# hooks

Hooks are predefined points where registered callback code can interact with or modify other code.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## How to stop AI coding agents from committing secrets to git

DevFeed: [How to stop AI coding agents from committing secrets to git](<https://devfeed.tech/articles/how-to-stop-ai-coding-agents-from-committing-secrets-to-git-139213.md>)

Original publisher: [Read original article](<https://nirmata.com/2026/11/18/how-to-stop-ai-coding-agents-from-committing-secrets-to-git/>)

Author: Ritesh Patel

Published: 2026-11-18T01:14:41.413057Z

Content type: tutorial

Language: en

Sources: [Nirmata](<https://devfeed.tech/sources/nirmata.md>)

Topics: [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Git](<https://devfeed.tech/topics/git.md>), [hooks](<https://devfeed.tech/topics/hooks.md>), [Secret Scanning](<https://devfeed.tech/topics/secret-scanning.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [ai-governance](<https://devfeed.tech/tags/ai-governance.md>), [coding](<https://devfeed.tech/tags/coding.md>), [commit](<https://devfeed.tech/tags/commit.md>), [git](<https://devfeed.tech/tags/git.md>), [git-hooks](<https://devfeed.tech/tags/git-hooks.md>), [github](<https://devfeed.tech/tags/github.md>), [hooks](<https://devfeed.tech/tags/hooks.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [pretooluse-hook](<https://devfeed.tech/tags/pretooluse-hook.md>), [protection](<https://devfeed.tech/tags/protection.md>), [push-protection](<https://devfeed.tech/tags/push-protection.md>), [rules](<https://devfeed.tech/tags/rules.md>), [secrets](<https://devfeed.tech/tags/secrets.md>), [secrets-management](<https://devfeed.tech/tags/secrets-management.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

No single layer fully prevents an AI coding agent from committing or pushing secrets. A Claude Code deny rule blocks common `git push` command forms but can miss variants; a PreToolUse hook can inspect the full command and refuse bypass flags such as `--no-verify`. A committed, executable Git pre-commit hook can inspect staged changes, though Git allows it to be skipped with that flag. GitHub push protection checks pushes server-side, including command-line pushes, but requires GitHub Secret Protection for repositories, is disabled by default, supports specific secret patterns, and permits write-access users to bypass by default. Together, these controls cover different gaps; the excerpt also notes limits involving other tools, wrapped commands, and secrets already in local history.

### Source excerpt

Block git push and commit from an AI coding agent with deny rules, a PreToolUse hook, git hooks and GitHub push protection, and see where each layer fails.

## I Ran 13 Claude Code Sessions at Once. Here's What the Data Revealed

DevFeed: [I Ran 13 Claude Code Sessions at Once. Here's What the Data Revealed](<https://devfeed.tech/articles/i-ran-13-claude-code-sessions-at-once-here-s-what-the-data-revealed-128452.md>)

Original publisher: [Read original article](<https://hackernoon.com/i-ran-13-claude-code-sessions-at-once-heres-what-the-data-revealed?source=rss>)

Author: Myeongseok Kang

Published: 2026-11-11T07:22:36Z

Content type: news

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [hooks](<https://devfeed.tech/topics/hooks.md>), [code security](<https://devfeed.tech/topics/code-security.md>), [versioning](<https://devfeed.tech/topics/versioning.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-isolation](<https://devfeed.tech/tags/ai-agent-isolation.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [app](<https://devfeed.tech/tags/app.md>), [block](<https://devfeed.tech/tags/block.md>), [checkout](<https://devfeed.tech/tags/checkout.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [claude-projects](<https://devfeed.tech/tags/claude-projects.md>), [command](<https://devfeed.tech/tags/command.md>), [commands](<https://devfeed.tech/tags/commands.md>), [commit](<https://devfeed.tech/tags/commit.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [git](<https://devfeed.tech/tags/git.md>), [git-worktree](<https://devfeed.tech/tags/git-worktree.md>), [git-worktree-add](<https://devfeed.tech/tags/git-worktree-add.md>), [git-worktree-conflicts](<https://devfeed.tech/tags/git-worktree-conflicts.md>), [github](<https://devfeed.tech/tags/github.md>), [guard](<https://devfeed.tech/tags/guard.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [rules](<https://devfeed.tech/tags/rules.md>), [sessions](<https://devfeed.tech/tags/sessions.md>), [shell](<https://devfeed.tech/tags/shell.md>), [transcripts](<https://devfeed.tech/tags/transcripts.md>)

### AI overview

Replaying two weeks of Claude Code history (204 sessions, 101,167 shell commands) against shared-machine guard rules flagged 507 commands that could interfere with another session. Twenty-five were `git add -A` commands in a tree where another session was active within ten minutes. The rules target broad staging, killing processes by name, port conflicts, disk scans, and removing an in-use worktree. As Claude Code hooks, they inspect matching commands before execution, block risky cases, and give the model a safer next step; the guards fail open if they cannot parse or inspect context. The scan is read-only and can be run on transcripts with claude-bulkhead. Its count is incomplete: historical transcripts lack port and memory state, so those checks were excluded, and a rule match does not establish that damage occurred. The command parser also cannot catch every script, alias, or encoded command, so the guards are not a sandbox.

### Source excerpt

Replaying two weeks of Claude Code transcripts through guard rules: 507 of 101,167 shell commands would have hurt another live session.

## Postman Plugin for Claude Code: A Hands-On Guide

DevFeed: [Postman Plugin for Claude Code: A Hands-On Guide](<https://devfeed.tech/articles/postman-plugin-for-claude-code-a-hands-on-guide-125770.md>)

Original publisher: [Read original article](<https://blog.postman.com/postman-plugin-for-claude-code-a-hands-on-guide/>)

Author: Quinton Wall

Published: 2026-11-09T16:00:00Z

Content type: tutorial

Language: en

Sources: [Postman](<https://devfeed.tech/sources/postman-blog.md>)

Topics: [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Postman](<https://devfeed.tech/topics/postman.md>), [OpenAPI Specification](<https://devfeed.tech/topics/openapi.md>), [Postman CLI](<https://devfeed.tech/topics/postman-cli.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [mock api](<https://devfeed.tech/topics/mock-api.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>), [Spec Driven Development](<https://devfeed.tech/topics/spec-driven-development.md>), [hooks](<https://devfeed.tech/topics/hooks.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-native](<https://devfeed.tech/tags/ai-native.md>), [api](<https://devfeed.tech/tags/api.md>), [blog](<https://devfeed.tech/tags/blog.md>), [build](<https://devfeed.tech/tags/build.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [code](<https://devfeed.tech/tags/code.md>), [copy](<https://devfeed.tech/tags/copy.md>), [editor-s-picks](<https://devfeed.tech/tags/editor-s-picks.md>), [editors-recommendations](<https://devfeed.tech/tags/editors-recommendations.md>), [first](<https://devfeed.tech/tags/first.md>), [gate](<https://devfeed.tech/tags/gate.md>), [general](<https://devfeed.tech/tags/general.md>), [guide](<https://devfeed.tech/tags/guide.md>), [hooks](<https://devfeed.tech/tags/hooks.md>), [install](<https://devfeed.tech/tags/install.md>), [mock](<https://devfeed.tech/tags/mock.md>), [native](<https://devfeed.tech/tags/native.md>), [openapi](<https://devfeed.tech/tags/openapi.md>), [plugin](<https://devfeed.tech/tags/plugin.md>), [post](<https://devfeed.tech/tags/post.md>), [postman](<https://devfeed.tech/tags/postman.md>), [postman-plugin](<https://devfeed.tech/tags/postman-plugin.md>)

### AI overview

The Postman plugin for Claude Code routes API work through Postman CLI skills, from discovery and contract design to mocks, tests, readiness scoring, and CI checks. The guide recommends keeping an OpenAPI spec and v3 collection in the repository, linting changes, and using a deterministic CI gate; local lint, mock, and collection commands do not require Postman sign-in, while cloud features do. Discovery searches Postman resources by ownership scope, Orbit finds third-party provider candidates but does not supply credentials, and Context Graph can identify endpoint consumers but not which fields they use. Mocks can exercise failure cases, though they do not prove the implementation works and do not hot-reload. Claude Code plan mode, hooks, subagents, and bounded `/goal` loops can make the process more repeatable; token and turn limits help constrain loops. The guide also cautions that CLI flags vary by version and some commands report results or analytics to Postman by default.

### Source excerpt

Install the Postman plugin for Claude Code, then build, mock, test, and gate an AI-native API with copy-paste prompts, hooks, and /goal. The post Postman Plugin for Claude Code: A Hands-On Guide appeared first on Postman Blog.

## 5 things CIOs must understand to govern Claude Code

DevFeed: [5 things CIOs must understand to govern Claude Code](<https://devfeed.tech/articles/5-things-cios-must-understand-to-govern-claude-code-121652.md>)

Original publisher: [Read original article](<https://www.cio.com/article/4245334/5-things-cios-must-understand-to-govern-claude-code.html>)

Author: CrowdStrike

Published: 2026-11-06T20:05:10Z

Content type: article

Language: en

Sources: [CIO](<https://devfeed.tech/sources/cio.md>)

Topics: [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [hooks](<https://devfeed.tech/topics/hooks.md>), [observability](<https://devfeed.tech/topics/observability.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [anthropic](<https://devfeed.tech/topics/anthropic.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-generative-ai](<https://devfeed.tech/tags/artificial-intelligence-generative-ai.md>), [cios](<https://devfeed.tech/tags/cios.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cloud-environments](<https://devfeed.tech/tags/cloud-environments.md>), [commands](<https://devfeed.tech/tags/commands.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [credentials](<https://devfeed.tech/tags/credentials.md>), [crowdstrike](<https://devfeed.tech/tags/crowdstrike.md>), [dependency](<https://devfeed.tech/tags/dependency.md>), [developers](<https://devfeed.tech/tags/developers.md>), [edition-us](<https://devfeed.tech/tags/edition-us.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [governance](<https://devfeed.tech/tags/governance.md>), [has](<https://devfeed.tech/tags/has.md>), [hooks](<https://devfeed.tech/tags/hooks.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [storytype-brandpost](<https://devfeed.tech/tags/storytype-brandpost.md>)

### AI overview

Claude Code can turn a developer's request into rapid actions across code, credentials, cloud environments, and connected services under that developer's permissions. The article recommends centrally managed settings and hooks to enforce rules at session and tool checkpoints, such as blocking sensitive commands, requiring approval, or logging activity. It cautions that hooks inspect proposed actions but may miss what scripts, MCP servers, or other processes do after launch, as well as risks formed between checkpoints. The proposed complement is runtime visibility into processes, file access, network connections, and credential use, linked back to the initiating prompt and session to support investigation and response. Hooks govern intent; runtime monitoring observes resulting activity. The excerpt also notes the challenge of tracking multiple agents across an organization.

### Source excerpt

Claude Code has quickly become one of the most widely adopted AI agents in the enterprise. Developers use it to write and refactor code, troubleshoot builds, run tests, and manage infrastructure, often by describing an objective and letting the agent determine the steps required to accomplish it. That autonomy is the point. It is also why Claude Code is a governance decision for CIOs, not just a developer tooling choice. Claude Code runs locally on employee workstations, executes commands with the developer's permissions, and can reach source code, credentials, cloud environments, and connected services as it works. Anthropic has given enterprises meaningful controls to govern how Claude Code behaves, including centrally managed settings and hooks. These controls are essential. But controls that evaluate what an agent intends to do are not the same as visibility into what it actually does. Here are five things CIOs need to understand to secure and govern Claude Code at enterprise scale. 1. Claude Code acts with your developers' authority Consider a developer who asks Claude Code to fix a failing build. The agent might read the codebase, install a dependency, run a setup script, edit a configuration file, query a cloud environment, and validate the result. One human instruction becomes a sequence of actions across multiple systems, all conducted with the developer's level of access. And it happens at machine speed. CrowdStrike internal usage data found that endpoint AI agents consumed roughly 700 times more tokens than humans using AI chatbots via the browser. Every one of those interactions is an opportunity for the agent to read, write, or execute something. For CIOs, the question is no longer whether Claude Code makes developers more productive. It is whether the organization can account for what the agent does on its behalf. 2. Claude Code hooks are a strong first line of governance Claude Code includes native governance capabilities that every enterprise deploym

## Agent hooks in Claude Code, Cursor, and Codex explained

DevFeed: [Agent hooks in Claude Code, Cursor, and Codex explained](<https://devfeed.tech/articles/agent-hooks-in-claude-code-cursor-and-codex-explained-113299.md>)

Original publisher: [Read original article](<https://www.avanderlee.com/ai-development/agent-hooks-claude-code-cursor-codex/>)

Author: Antoine van der Lee

Published: 2026-11-02T10:13:46Z

Content type: article

Language: en

Sources: [SwiftLee](<https://devfeed.tech/sources/swiftlee.md>)

Topics: [hooks](<https://devfeed.tech/topics/hooks.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-hooks](<https://devfeed.tech/tags/agent-hooks.md>), [agent-skills](<https://devfeed.tech/tags/agent-skills.md>), [agents](<https://devfeed.tech/tags/agents.md>), [agents-md](<https://devfeed.tech/tags/agents-md.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-development](<https://devfeed.tech/tags/ai-development.md>), [automate](<https://devfeed.tech/tags/automate.md>), [automatically](<https://devfeed.tech/tags/automatically.md>), [bash](<https://devfeed.tech/tags/bash.md>), [block](<https://devfeed.tech/tags/block.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [claude-code-hooks](<https://devfeed.tech/tags/claude-code-hooks.md>), [codex](<https://devfeed.tech/tags/codex.md>), [command](<https://devfeed.tech/tags/command.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [hooks](<https://devfeed.tech/tags/hooks.md>), [scripts](<https://devfeed.tech/tags/scripts.md>), [shell](<https://devfeed.tech/tags/shell.md>)

### AI overview

Hooks run scripts at defined agent events, so they can enforce repeated rules more reliably than instructions in AGENTS.md, which the model may forget. A hook has an event, an optional filter, a script receiving event details as JSON on stdin, and an action; pre-action hooks can block or change a call, while post-action hooks cannot undo it. Claude Code and Codex share an event/matcher/handler configuration shape; Cursor uses a flatter hooks.json format, and tool names differ (Bash versus Shell). Codex requires review and trust for hooks, while Cursor limits project hooks to trusted workspaces. The example hook blocks unfiltered xcodebuild build/test commands and suggests piping output through xcsift; it fails open if input is unexpected or jq is missing. The article advises reading scripts before enabling them, keeping hooks fast, choosing failure behavior deliberately, and not relying on hooks as the only safeguard because some paths may skip them.

### Source excerpt

Agent hooks are small scripts that your agent tool runs automatically when something happens, like right before a shell command or when the agent finishes. Claude Code hooks, Cursor hooks, and Codex hooks all work this way, and they are the most reliable way to make sure a rule is followed every time. I use ... -> The post Agent hooks in Claude Code, Cursor, and Codex explained appeared first on SwiftLee.

## Governing Claude Code, Cursor and Copilot with one policy

DevFeed: [Governing Claude Code, Cursor and Copilot with one policy](<https://devfeed.tech/articles/governing-claude-code-cursor-and-copilot-with-one-policy-119456.md>)

Original publisher: [Read original article](<https://nirmata.com/2026/10/31/governing-claude-code-cursor-and-copilot-with-one-policy/>)

Author: Ritesh Patel

Published: 2026-10-31T15:00:00Z

Content type: comparison

Language: en

Sources: [Nirmata](<https://devfeed.tech/sources/nirmata.md>)

Topics: [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [hooks](<https://devfeed.tech/topics/hooks.md>), [MSP MCP](<https://devfeed.tech/topics/msp-mcp.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [2026](<https://devfeed.tech/tags/2026.md>), [3](<https://devfeed.tech/tags/3.md>), [admin](<https://devfeed.tech/tags/admin.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-sandbox](<https://devfeed.tech/tags/agent-sandbox.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-governance](<https://devfeed.tech/tags/ai-governance.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [code](<https://devfeed.tech/tags/code.md>), [compare](<https://devfeed.tech/tags/compare.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [hooks](<https://devfeed.tech/tags/hooks.md>), [limits](<https://devfeed.tech/tags/limits.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [network](<https://devfeed.tech/tags/network.md>), [one](<https://devfeed.tech/tags/one.md>), [permissions](<https://devfeed.tech/tags/permissions.md>), [policy](<https://devfeed.tech/tags/policy.md>), [security](<https://devfeed.tech/tags/security.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

No single policy file governs Claude Code, Cursor and Copilot; administrators must map one written policy to each tool's separate controls. Claude Code offers managed settings with permission and MCP allowlists, plus an OS sandbox for shell commands; its file tools, hooks and MCP processes remain outside that sandbox. Cursor combines dashboard team rules with Enterprise controls: only enforced rules are mandatory, and org-wide sandbox enforcement requires Enterprise. Copilot's cloud-agent firewall can be centrally configured with organization allowlists, but applies only to processes started through Bash, not MCP server processes. The excerpt's checklist recommends centralizing each tool's supported settings and recording undocumented controls as open items; it cautions that vendor documentation may change.

### Source excerpt

Claude Code, Cursor and Copilot each have different admin controls. Compare their permissions, MCP, hooks and network limits, and see where each one stops.

## Claude Code Mods: Custom Hooks to Fix My Biggest AI Coding Frustrations

DevFeed: [Claude Code Mods: Custom Hooks to Fix My Biggest AI Coding Frustrations](<https://devfeed.tech/articles/claude-code-mods-custom-hooks-to-fix-my-biggest-ai-coding-frustrations-107782.md>)

Original publisher: [Read original article](<https://towardsdatascience.com/claude-code-mods-custom-hooks-to-fix-my-biggest-ai-coding-frustrations/>)

Author: Chien Vu Minh

Published: 2026-10-30T11:00:00Z

Content type: tutorial

Language: en

Sources: [Towards Data Science](<https://devfeed.tech/sources/towards-data-science.md>)

Topics: [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [hooks](<https://devfeed.tech/topics/hooks.md>), [extend](<https://devfeed.tech/topics/extend.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [policy-as-code](<https://devfeed.tech/topics/policy-as-code.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Vibe coding](<https://devfeed.tech/topics/vibe-coding.md>), [Exception](<https://devfeed.tech/topics/exception.md>), [Process](<https://devfeed.tech/topics/process.md>), [To-Do](<https://devfeed.tech/topics/todo.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [codex](<https://devfeed.tech/topics/codex.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai-coding-assistants](<https://devfeed.tech/tags/ai-coding-assistants.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [api](<https://devfeed.tech/tags/api.md>), [api-key](<https://devfeed.tech/tags/api-key.md>), [api-keys](<https://devfeed.tech/tags/api-keys.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [aws](<https://devfeed.tech/tags/aws.md>), [base64](<https://devfeed.tech/tags/base64.md>), [bash](<https://devfeed.tech/tags/bash.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [code](<https://devfeed.tech/tags/code.md>), [context](<https://devfeed.tech/tags/context.md>), [custom](<https://devfeed.tech/tags/custom.md>), [developer-productivity](<https://devfeed.tech/tags/developer-productivity.md>), [editor-s-picks](<https://devfeed.tech/tags/editor-s-picks.md>), [hooks](<https://devfeed.tech/tags/hooks.md>), [overhead](<https://devfeed.tech/tags/overhead.md>), [plan](<https://devfeed.tech/tags/plan.md>), [progress](<https://devfeed.tech/tags/progress.md>), [tests](<https://devfeed.tech/tags/tests.md>)

### AI overview

The article describes four Claude Code mods that automate repeated workflow checks: secret-guard masks recognized `.env` values and blocks some risky commands; done-gate warns when tasks are marked complete without a passing test after code changes; plan-meter displays plan progress; and context-meter shows context usage and can request compaction. In replay tests, secret-guard's value mode blocked 2 of 369 harmless calls and stopped or redacted 10 of 12 crafted leaks, while command mode blocked 157 harmless calls and stopped 7 leaks. Neither is a security boundary. A simple mod check took 0.27 ms in the test harness and a median 0.6 ms live, compared with 55-99 ms for fresh-process settings hooks on one Windows machine. The four mods passed 135 tests on Claude Code 2.1.296. Mods run with the user's permissions, are not sandboxed, and may access files or start programs through declared API calls, so the author advises reviewing those calls before installation.

### Source excerpt

How I built four Claude Code mods to protect API keys, track plan progress, catch untested code, and monitor context usage -- with 135 passing tests and up to 100x less overhead than traditional hooks -- and why they can outperform traditional hooks. The post Claude Code Mods: Custom Hooks to Fix My Biggest AI Coding Frustrations appeared first on Towards Data Science.

## How to audit MCP tool calls

DevFeed: [How to audit MCP tool calls](<https://devfeed.tech/articles/how-to-audit-mcp-tool-calls-104671.md>)

Original publisher: [Read original article](<https://nirmata.com/2026/10/26/how-to-audit-mcp-tool-calls/>)

Author: Ritesh Patel

Published: 2026-10-26T15:00:00Z

Content type: tutorial

Language: en

Sources: [Nirmata](<https://devfeed.tech/sources/nirmata.md>)

Topics: [audit](<https://devfeed.tech/topics/audit.md>), [API Logging](<https://devfeed.tech/topics/api-logging.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>), [hooks](<https://devfeed.tech/topics/hooks.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-governance](<https://devfeed.tech/tags/ai-governance.md>), [argument](<https://devfeed.tech/tags/argument.md>), [arguments](<https://devfeed.tech/tags/arguments.md>), [audit](<https://devfeed.tech/tags/audit.md>), [audit-trail](<https://devfeed.tech/tags/audit-trail.md>), [chmod](<https://devfeed.tech/tags/chmod.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cli](<https://devfeed.tech/tags/cli.md>), [collector](<https://devfeed.tech/tags/collector.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [events](<https://devfeed.tech/tags/events.md>), [hooks](<https://devfeed.tech/tags/hooks.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-tool](<https://devfeed.tech/tags/mcp-tool.md>), [opentelemetry](<https://devfeed.tech/tags/opentelemetry.md>), [otel](<https://devfeed.tech/tags/otel.md>), [security](<https://devfeed.tech/tags/security.md>), [server](<https://devfeed.tech/tags/server.md>), [source](<https://devfeed.tech/tags/source.md>), [tool](<https://devfeed.tech/tags/tool.md>)

### AI overview

Claude Code's MCP audit relies on OpenTelemetry events plus hooks: enable telemetry and the logs exporter, then set `OTEL_LOG_TOOL_DETAILS=1` to capture server and tool names and arguments. Join each `tool_decision` with its `tool_result` and hook record using `tool_use_id`; rejected calls appear in `tool_decision` but have no result, while failed calls have a result with `success` set to `false`. Hooks add the server's source and, for auto mode denials, a reason. The `mcp_server` hook field requires Claude Code v2.1.274 or later. Event arguments may be truncated, hook logs are locally editable, and arguments or responses may contain sensitive data; the article recommends relying on the collector as the record. Managed settings can lock exporter settings, while repository settings cannot set exporter variables. The article says the setup works without AIControls and makes no claim about what its gateway records.

### Source excerpt

Audit MCP tool calls in Claude Code with OpenTelemetry tool events and OTEL_LOG_TOOL_DETAILS=1, plus hooks that record each server's source and denied calls.

## How to block destructive commands in Claude Code

DevFeed: [How to block destructive commands in Claude Code](<https://devfeed.tech/articles/how-to-block-destructive-commands-in-claude-code-104664.md>)

Original publisher: [Read original article](<https://nirmata.com/2026/10/24/how-to-block-destructive-commands-in-claude-code/>)

Author: Ritesh Patel

Published: 2026-10-24T19:00:00Z

Content type: tutorial

Language: en

Sources: [Nirmata](<https://devfeed.tech/sources/nirmata.md>)

Topics: [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [hooks](<https://devfeed.tech/topics/hooks.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-governance](<https://devfeed.tech/tags/ai-governance.md>), [bash](<https://devfeed.tech/tags/bash.md>), [block](<https://devfeed.tech/tags/block.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [commands](<https://devfeed.tech/tags/commands.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [layer](<https://devfeed.tech/tags/layer.md>), [managed](<https://devfeed.tech/tags/managed.md>), [pretooluse-hook](<https://devfeed.tech/tags/pretooluse-hook.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

Claude Code deny rules block matching Bash commands before allow rules are considered and can cover chained commands, leading variable assignments, subshells and loops. But they match the command text Claude writes, so `Bash(rm *)` misses forms such as `/bin/rm` and `sh -c "rm ..."`; they are a guard, not a security boundary. A `PreToolUse` hook can block calls by exiting with code 2, but the excerpt's simple example checks only whether the entire command starts with `rm`, so it misses chained commands unless expanded to inspect each part. The layers stack: hooks can add restrictions but cannot override a deny. Project rules in committed `.claude/settings.json` share policy across a repository; managed settings apply machine-wide and managed denies cannot be overridden by lower-level settings. Local administrators can still edit the managed file, so the excerpt recommends device management to redeploy it. `/status` shows loaded settings sources, while `claude doctor` reports rejected entries; test matching with a harmless command.

### Source excerpt

Block rm -rf and other destructive Claude Code commands with Bash deny rules, a PreToolUse hook and managed settings. Learn where each layer stops and fails.

## Inside the LiteLLM 1.107.0 supply chain compromise: Credential theft through Python startup hooks

DevFeed: [Inside the LiteLLM 1.107.0 supply chain compromise: Credential theft through Python startup hooks](<https://devfeed.tech/articles/inside-the-litellm-1-107-0-supply-chain-compromise-credential-theft-through-python-startup-hooks-98535.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/security/blog/2026/10/23/inside-the-litellm-1-107-0-supply-chain-compromise-credential-theft-through-python-startup-hooks/>)

Author: Microsoft Security Research, Mahesh Mandava, Srinivasan Govindarajan, Sagar Patil and Suriyaraj Natarajan

Published: 2026-10-23T18:12:19Z

Content type: news

Language: en

Sources: [Microsoft Security](<https://devfeed.tech/sources/microsoft-security-blog.md>)

Topics: [litellm attack](<https://devfeed.tech/topics/litellm-attack.md>), [Credential theft](<https://devfeed.tech/topics/credential-theft.md>), [software supply-chain attack](<https://devfeed.tech/topics/software-supply-chain-attack.md>), [litellm](<https://devfeed.tech/topics/litellm.md>), [malicious packages](<https://devfeed.tech/topics/malicious-packages.md>), [supply-chain-security](<https://devfeed.tech/topics/supply-chain-security.md>), [Endpoint security](<https://devfeed.tech/topics/endpoint-security.md>), [Threat monitoring](<https://devfeed.tech/topics/threat-monitoring.md>), [hooks](<https://devfeed.tech/topics/hooks.md>), [credential-based attacks](<https://devfeed.tech/topics/credential-based-attacks.md>), [import](<https://devfeed.tech/topics/import.md>), [AI software supply chain security](<https://devfeed.tech/topics/ai-software-supply-chain-security.md>)

Tags: [compromise](<https://devfeed.tech/tags/compromise.md>), [credential-theft](<https://devfeed.tech/tags/credential-theft.md>), [hooks](<https://devfeed.tech/tags/hooks.md>), [litellm](<https://devfeed.tech/tags/litellm.md>), [python](<https://devfeed.tech/tags/python.md>), [startup](<https://devfeed.tech/tags/startup.md>), [supply-chain](<https://devfeed.tech/tags/supply-chain.md>), [supply-chain-attack](<https://devfeed.tech/tags/supply-chain-attack.md>), [supply-chain-compromise](<https://devfeed.tech/tags/supply-chain-compromise.md>)

### AI overview

LiteLLM 1.107.0 carried Python startup files that could launch credential theft whenever Python started in an affected environment, even if an application never imported LiteLLM. The recovered collector gathered accessible developer, cloud, browser, infrastructure, and LiteLLM proxy data, encrypted it, and attempted to send it to an attacker-controlled endpoint. A separate Unix-oriented loader could retrieve and execute more Python code, but Microsoft did not confirm that second-stage activity. The excerpt says package presence alone does not prove collection or compromise, and deleting the LiteLLM directory may leave startup files behind. Response guidance includes isolating affected systems, avoiding Python or pip there during investigation, rebuilding from verified artifacts, rotating reachable credentials from a clean machine, and correlating hashes, process, network, and identity evidence. Microsoft also provides Defender detections and hunting queries, which are investigation leads rather than standalone verdicts.

### Source excerpt

Microsoft Threat Intelligence analyzes the LiteLLM 1.107.0 compromise, including Python startup hooks, credential theft, remote code loading, detections, and mitigations. The post Inside the LiteLLM 1.107.0 supply chain compromise: Credential theft through Python startup hooks appeared first on Microsoft Security Blog.

## How to Automate Your Workflow With Claude Code Hooks

DevFeed: [How to Automate Your Workflow With Claude Code Hooks](<https://devfeed.tech/articles/how-to-automate-your-workflow-with-claude-code-hooks-89976.md>)

Original publisher: [Read original article](<https://realpython.com/claude-code-hooks/>)

Author: Vivek Sahu

Published: 2026-10-19T14:00:00Z

Content type: tutorial

Language: en

Sources: [Real Python](<https://devfeed.tech/sources/real-python.md>)

Topics: [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [hooks](<https://devfeed.tech/topics/hooks.md>), [anthropic](<https://devfeed.tech/topics/anthropic.md>)

Tags: [claude-code](<https://devfeed.tech/tags/claude-code.md>), [claude-code-hooks](<https://devfeed.tech/tags/claude-code-hooks.md>), [python](<https://devfeed.tech/tags/python.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

This tutorial shows how to configure Claude Code hooks for desktop notifications, enforcing project tool choices, and automatically formatting edited Python files with Ruff. It explains the Stop, PreToolUse, and PostToolUse events, how matchers select tools, and how exit codes can block a command and give Claude feedback.

### Source excerpt

Learn how to use Claude Code hooks that auto-format your Python code after every edit, enforce your chosen tools, and ping you when a task finishes.

## Quiz: How to Automate Your Workflow With Claude Code Hooks

DevFeed: [Quiz: How to Automate Your Workflow With Claude Code Hooks](<https://devfeed.tech/articles/quiz-how-to-automate-your-workflow-with-claude-code-hooks-89977.md>)

Original publisher: [Read original article](<https://realpython.com/quizzes/claude-code-hooks/>)

Author: Real Python

Published: 2026-10-19T12:00:00Z

Content type: tutorial

Language: en

Sources: [Real Python](<https://devfeed.tech/sources/real-python.md>)

Topics: [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [hooks](<https://devfeed.tech/topics/hooks.md>)

Tags: [claude-code](<https://devfeed.tech/tags/claude-code.md>), [claude-code-hooks](<https://devfeed.tech/tags/claude-code-hooks.md>), [code](<https://devfeed.tech/tags/code.md>), [events](<https://devfeed.tech/tags/events.md>), [exit](<https://devfeed.tech/tags/exit.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [tools](<https://devfeed.tech/tags/tools.md>), [tutorial](<https://devfeed.tech/tags/tutorial.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

An interactive seven-question quiz checks understanding of Claude Code hooks, including hook components, events before and after tool calls, and exit codes that can block or redirect actions. It has no time limit and awards points for correct answers.

### Source excerpt

Test your understanding of Claude Code hooks, including the Stop, PreToolUse, and PostToolUse events and the exit codes that block an action.

## Claude Code Hooks: Enforce Project Conventions with Gates and Linting

DevFeed: [Claude Code Hooks: Enforce Project Conventions with Gates and Linting](<https://devfeed.tech/articles/claude-code-hooks-enforce-project-conventions-with-gates-and-linting-89682.md>)

Original publisher: [Read original article](<https://www.sitepoint.com/claude-code-hooks-enforce-project-conventions/>)

Author: SitePoint Team

Published: 2026-10-18T15:43:10Z

Content type: tutorial

Language: en

Sources: [SitePoint](<https://devfeed.tech/sources/sitepoint.md>)

Topics: [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [hooks](<https://devfeed.tech/topics/hooks.md>), [ESLint](<https://devfeed.tech/topics/eslint.md>), [Prettier](<https://devfeed.tech/topics/prettier.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [claude-code-hooks](<https://devfeed.tech/tags/claude-code-hooks.md>), [eslint](<https://devfeed.tech/tags/eslint.md>), [linting](<https://devfeed.tech/tags/linting.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [programming](<https://devfeed.tech/tags/programming.md>)

### AI overview

This tutorial shows how to configure Claude Code hooks to enforce project conventions during agentic coding. It builds a pre-write gate to prompt checks for existing implementations and a post-edit pipeline that runs Prettier and ESLint, while covering hook events, exit codes, state management, and implementation caveats.

### Source excerpt

Configure Claude Code hooks to enforce project conventions: a pre-write gate that stops duplicate code, and a post-edit pipeline that runs Prettier and ESLint. Continue reading Claude Code Hooks: Enforce Project Conventions with Gates and Linting on SitePoint.

## Systemtap 5.6 released

DevFeed: [Systemtap 5.6 released](<https://devfeed.tech/articles/systemtap-5-6-released-42772.md>)

Original publisher: [Read original article](<https://lwn.net/Articles/1095220/>)

Author: corbet

Published: 2026-09-18T12:58:42Z

Content type: release

Language: en

Sources: [LWN.net](<https://devfeed.tech/sources/lwn-net.md>)

Topics: [tracing](<https://devfeed.tech/topics/tracing.md>), [Kernel](<https://devfeed.tech/topics/kernel.md>), [Linux](<https://devfeed.tech/topics/linux.md>), [processing](<https://devfeed.tech/topics/processing.md>), [systemd](<https://devfeed.tech/topics/systemd.md>), [hooks](<https://devfeed.tech/topics/hooks.md>)

Tags: [hooks](<https://devfeed.tech/tags/hooks.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [linux](<https://devfeed.tech/tags/linux.md>), [processing](<https://devfeed.tech/tags/processing.md>), [service](<https://devfeed.tech/tags/service.md>), [systemd](<https://devfeed.tech/tags/systemd.md>), [tracepoint](<https://devfeed.tech/tags/tracepoint.md>), [tracing](<https://devfeed.tech/tags/tracing.md>), [version](<https://devfeed.tech/tags/version.md>)

### AI overview

SystemTap 5.6 has been released with new BPF LSM and XDP probes, BTF-based kernel tracepoint probes, statement execution tracing, improved runtime error context, dyninst hardware watchpoints, updated systemd service templates, Linux 7.2 compatibility work, and multithreaded performance improvements.

### Source excerpt

Version 5.6 of the Systemtap tracing tool has been released. BPF LSM hooks and XDP packet-processing probes for the --bpf runtime, BTF-based kernel.tracepoint probes, statement execution tracing, a new @enumname() operator, richer runtime error context, dyninst hardware watchpoints, modern systemd service templates, and broad Linux 7.2 runtime/tapset compatibility work. Multithreaded speedups throughout.

## Audit your Agent files

DevFeed: [Audit your Agent files](<https://devfeed.tech/articles/audit-your-agent-files-55612.md>)

Original publisher: [Read original article](<https://addyosmani.com/blog/audit-your-agent-files/>)

Author: Addy Osmani

Published: 2026-08-27T00:00:00Z

Content type: article

Language: en

Sources: [Addy Osmani](<https://devfeed.tech/sources/addy-osmani.md>)

Topics: [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [Programming](<https://devfeed.tech/topics/programming.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [configuration](<https://devfeed.tech/topics/configuration.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [abstraction](<https://devfeed.tech/topics/abstraction.md>), [hooks](<https://devfeed.tech/topics/hooks.md>), [sdlc](<https://devfeed.tech/topics/sdlc.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-skill](<https://devfeed.tech/tags/agent-skill.md>), [agent-skills](<https://devfeed.tech/tags/agent-skills.md>), [agents](<https://devfeed.tech/tags/agents.md>), [audit](<https://devfeed.tech/tags/audit.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-md](<https://devfeed.tech/tags/claude-md.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [files](<https://devfeed.tech/tags/files.md>), [guide](<https://devfeed.tech/tags/guide.md>), [hooks](<https://devfeed.tech/tags/hooks.md>), [markdown-files](<https://devfeed.tech/tags/markdown-files.md>), [practical](<https://devfeed.tech/tags/practical.md>), [sdlc](<https://devfeed.tech/tags/sdlc.md>), [skills](<https://devfeed.tech/tags/skills.md>), [token-costs](<https://devfeed.tech/tags/token-costs.md>)

### AI overview

A practical guide to auditing coding-agent configuration files, including CLAUDE.md, AGENTS.md, skills, hooks, and memory. It discusses how model and harness improvements can make older instructions obsolete, increase token costs, or reduce agent quality, and recommends periodically reassessing what remains useful.

### Source excerpt

A practical guide to auditing what your coding agent still needs.

## Bring your own hook: a 5-line PostToolUse template calling sonar analyze agentic

DevFeed: [Bring your own hook: a 5-line PostToolUse template calling sonar analyze agentic](<https://devfeed.tech/articles/bring-your-own-hook-a-5-line-posttooluse-template-calling-sonar-analyze-agentic-50223.md>)

Original publisher: [Read original article](<https://www.sonarsource.com/blog/bring-your-own-hook/>)

Author: Prasenjit Sarkar

Published: 2026-08-24T13:00:00Z

Content type: tutorial

Language: en

Sources: [Sonar Blog](<https://devfeed.tech/sources/sonar-blog.md>)

Topics: [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Bash](<https://devfeed.tech/topics/bash.md>), [Code](<https://devfeed.tech/topics/code.md>), [Command-line interface](<https://devfeed.tech/topics/cli.md>), [Continuous integration](<https://devfeed.tech/topics/continuous-integration.md>), [hooks](<https://devfeed.tech/topics/hooks.md>), [JSON](<https://devfeed.tech/topics/json.md>)

Tags: [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [agentic-development](<https://devfeed.tech/tags/agentic-development.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [ai-generated-code](<https://devfeed.tech/tags/ai-generated-code.md>), [bash](<https://devfeed.tech/tags/bash.md>), [bash-hook-script](<https://devfeed.tech/tags/bash-hook-script.md>), [ci](<https://devfeed.tech/tags/ci.md>), [ci-grade-feedback](<https://devfeed.tech/tags/ci-grade-feedback.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [claude-code-hooks](<https://devfeed.tech/tags/claude-code-hooks.md>), [cli](<https://devfeed.tech/tags/cli.md>), [code](<https://devfeed.tech/tags/code.md>), [code-quality](<https://devfeed.tech/tags/code-quality.md>), [code-verification](<https://devfeed.tech/tags/code-verification.md>), [developer-guide](<https://devfeed.tech/tags/developer-guide.md>), [exit-code-51](<https://devfeed.tech/tags/exit-code-51.md>), [hooks](<https://devfeed.tech/tags/hooks.md>), [json](<https://devfeed.tech/tags/json.md>), [posttooluse-hook](<https://devfeed.tech/tags/posttooluse-hook.md>), [sonar-analyze-agentic](<https://devfeed.tech/tags/sonar-analyze-agentic.md>), [sonar-vortex](<https://devfeed.tech/tags/sonar-vortex.md>), [sonarqube](<https://devfeed.tech/tags/sonarqube.md>), [sonarqube-agentic-analysis](<https://devfeed.tech/tags/sonarqube-agentic-analysis.md>), [sql-injection](<https://devfeed.tech/tags/sql-injection.md>), [static-analysis](<https://devfeed.tech/tags/static-analysis.md>), [taint-analysis](<https://devfeed.tech/tags/taint-analysis.md>)

### AI overview

A tutorial for configuring a minimal Claude Code PostToolUse hook that runs SonarQube Agentic Analysis on files after they are edited. It explains the required SonarQube setup, JSON input, exit-code behavior, and analysis depth.

### Source excerpt

Set up a minimal SonarQube Agentic Analysis hook in Claude Code with five lines of Bash and understand how exit codes control feedback.

## Claude Code hooks and how Sonar Vortex verifies AI code inside the loop

DevFeed: [Claude Code hooks and how Sonar Vortex verifies AI code inside the loop](<https://devfeed.tech/articles/claude-code-hooks-and-how-sonar-vortex-verifies-ai-code-inside-the-loop-50224.md>)

Original publisher: [Read original article](<https://www.sonarsource.com/blog/claude-code-hooks-and-how-sonar-vortex-verifies-ai-code/>)

Author: Prasenjit Sarkar

Published: 2026-08-17T13:00:00Z

Content type: tutorial

Language: en

Sources: [Sonar Blog](<https://devfeed.tech/sources/sonar-blog.md>)

Topics: [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [hooks](<https://devfeed.tech/topics/hooks.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [software-development](<https://devfeed.tech/topics/software-development.md>), [reliability-engineering](<https://devfeed.tech/topics/reliability-engineering.md>), [Code](<https://devfeed.tech/topics/code.md>), [prompt](<https://devfeed.tech/topics/prompt.md>)

Tags: [agentic-analysis](<https://devfeed.tech/tags/agentic-analysis.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-code-verification](<https://devfeed.tech/tags/ai-code-verification.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [ai-generated-code](<https://devfeed.tech/tags/ai-generated-code.md>), [ai-guardrails](<https://devfeed.tech/tags/ai-guardrails.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [claude-code-hooks](<https://devfeed.tech/tags/claude-code-hooks.md>), [code](<https://devfeed.tech/tags/code.md>), [code-quality](<https://devfeed.tech/tags/code-quality.md>), [code-security](<https://devfeed.tech/tags/code-security.md>), [deterministic-guardrails](<https://devfeed.tech/tags/deterministic-guardrails.md>), [developer-security](<https://devfeed.tech/tags/developer-security.md>), [development](<https://devfeed.tech/tags/development.md>), [hook-security](<https://devfeed.tech/tags/hook-security.md>), [mcp-server](<https://devfeed.tech/tags/mcp-server.md>), [posttooluse-hook](<https://devfeed.tech/tags/posttooluse-hook.md>), [pretooluse-hook](<https://devfeed.tech/tags/pretooluse-hook.md>), [reliability](<https://devfeed.tech/tags/reliability.md>), [secrets-detection](<https://devfeed.tech/tags/secrets-detection.md>), [software-development-lifecycle](<https://devfeed.tech/tags/software-development-lifecycle.md>), [sonar-vortex](<https://devfeed.tech/tags/sonar-vortex.md>), [sonarqube](<https://devfeed.tech/tags/sonarqube.md>), [static-analysis](<https://devfeed.tech/tags/static-analysis.md>), [trust](<https://devfeed.tech/tags/trust.md>)

### AI overview

A hands-on guide to Claude Code hooks, covering their event model, JSON contract, and scripts for enforcing deterministic guardrails around AI coding agents. It also explains how Sonar Vortex applies the same mechanism to verify AI-generated code inside the development loop.

### Source excerpt

Learn how Claude Code hooks enforce deterministic AI guardrails and how Sonar Vortex verifies AI generated code inside the development loop.

## 13 million tool calls: auditing every AI coding agent action with Elastic Agent

DevFeed: [13 million tool calls: auditing every AI coding agent action with Elastic Agent](<https://devfeed.tech/articles/13-million-tool-calls-auditing-every-ai-coding-agent-action-with-elastic-agent-48840.md>)

Original publisher: [Read original article](<https://www.elastic.co/security-labs/blog/ai-coding-agent-audit-cursor-hooks>)

Author: Wieger van der Meulen

Published: 2026-08-11T00:00:00Z

Content type: tutorial

Language: en

Sources: [Elastic Security Labs](<https://devfeed.tech/sources/elastic-security-labs.md>)

Topics: [cursor](<https://devfeed.tech/topics/cursor.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [hooks](<https://devfeed.tech/topics/hooks.md>), [elasticsearch](<https://devfeed.tech/topics/elasticsearch.md>), [observability](<https://devfeed.tech/topics/observability.md>), [Security Information and Event Management (SIEM)](<https://devfeed.tech/topics/siem-security.md>), [Command-line interface](<https://devfeed.tech/topics/cli.md>), [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [Shell](<https://devfeed.tech/topics/shell.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai-automation](<https://devfeed.tech/tags/ai-automation.md>), [ai-coding-agent](<https://devfeed.tech/tags/ai-coding-agent.md>), [bash](<https://devfeed.tech/tags/bash.md>), [cli](<https://devfeed.tech/tags/cli.md>), [coding](<https://devfeed.tech/tags/coding.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [elasticsearch](<https://devfeed.tech/tags/elasticsearch.md>), [hooks](<https://devfeed.tech/tags/hooks.md>), [incident](<https://devfeed.tech/tags/incident.md>), [logs](<https://devfeed.tech/tags/logs.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [privacy](<https://devfeed.tech/tags/privacy.md>)

### AI overview

This tutorial shows how to audit AI coding agent activity using Cursor hooks, a dependency-free Bash collector, Elastic Agent, Elasticsearch, and ES|QL. It covers capturing tool calls, shell commands, file reads, and MCP requests, deploying the collector, parsing events, hunting activity, and addressing hardening and privacy concerns.

### Source excerpt

Cursor hooks and Elastic Agent capture every tool call, shell command, file read and MCP request as structured events you can hunt with ES|QL.

## Varonis Atlas Now Integrates with Claude Inference Hooks to Extend Real-Time AI Data Protection

DevFeed: [Varonis Atlas Now Integrates with Claude Inference Hooks to Extend Real-Time AI Data Protection](<https://devfeed.tech/articles/varonis-atlas-now-integrates-with-claude-inference-hooks-to-extend-real-time-ai-data-protection-54672.md>)

Original publisher: [Read original article](<https://www.varonis.com/blog/varonis-atlas-claude-inference-hooks-integration>)

Author: Nolan Necoechea

Published: 2026-08-07T23:47:27Z

Content type: release

Language: en

Sources: [Varonis](<https://devfeed.tech/sources/varonis-blog.md>)

Topics: [Claude](<https://devfeed.tech/topics/claude.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [hooks](<https://devfeed.tech/topics/hooks.md>), [prompt injection](<https://devfeed.tech/topics/prompt-injection.md>), [Security](<https://devfeed.tech/topics/security.md>), [sensitive data](<https://devfeed.tech/topics/sensitive-data.md>)

Tags: [ai-security](<https://devfeed.tech/tags/ai-security.md>), [claude](<https://devfeed.tech/tags/claude.md>), [data-security](<https://devfeed.tech/tags/data-security.md>), [hooks](<https://devfeed.tech/tags/hooks.md>), [inference](<https://devfeed.tech/tags/inference.md>), [prompt-injection](<https://devfeed.tech/tags/prompt-injection.md>), [protection](<https://devfeed.tech/tags/protection.md>), [security](<https://devfeed.tech/tags/security.md>), [sensitive-data](<https://devfeed.tech/tags/sensitive-data.md>)

### AI overview

Varonis Atlas integrates with Claude Inference hooks to inspect prompts and attachments through an AI security server before inference. It evaluates requests against customizable policies and can deny prompts involving sensitive data, prompt injection, or other policy violations before they reach Claude.

### Source excerpt

Varonis Atlas now integrates with Claude Inference hooks, routing prompts through an AI security server for real-time allow-or-deny verdicts before inference runs. That inspection happens ahead of Claude ever seeing the prompt -- the request is sent off for review and policy evaluation first. If it violates policy, it never reaches the model. Support for Inference hooks helps security teams prevent sensitive data exposure, prompt injection attempts, and other risky activity.

## Octane: Inferno's Successor Compiles React's Programming Model Ahead of Time

DevFeed: [Octane: Inferno's Successor Compiles React's Programming Model Ahead of Time](<https://devfeed.tech/articles/octane-inferno-s-successor-compiles-react-s-programming-model-ahead-of-time-56239.md>)

Original publisher: [Read original article](<https://www.developersdigest.tech/blog/octane-react-compiled-framework-2026>)

Author: Developers Digest

Published: 2026-08-03T00:00:00Z

Content type: article

Language: en

Sources: [Developers Digest](<https://devfeed.tech/sources/developers-digest.md>)

Topics: [React](<https://devfeed.tech/topics/react.md>), [Framework](<https://devfeed.tech/topics/framework.md>), [Programming](<https://devfeed.tech/topics/programming.md>), [Document Object Model (DOM)](<https://devfeed.tech/topics/dom.md>), [hooks](<https://devfeed.tech/topics/hooks.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [code](<https://devfeed.tech/tags/code.md>), [compilers](<https://devfeed.tech/tags/compilers.md>), [framework](<https://devfeed.tech/tags/framework.md>), [frontend](<https://devfeed.tech/tags/frontend.md>), [hooks](<https://devfeed.tech/tags/hooks.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [mit](<https://devfeed.tech/tags/mit.md>), [news](<https://devfeed.tech/tags/news.md>), [programming](<https://devfeed.tech/tags/programming.md>), [react](<https://devfeed.tech/tags/react.md>)

### AI overview

Octane is a new MIT-licensed UI framework from Inferno's creator. It compiles React-style hooks, Suspense, and actions into direct DOM code, without a virtual DOM, hook rules, or manually maintained dependency arrays. The document also mentions benchmarks and implications for teams and AI agents.

### Source excerpt

Octane is a new MIT-licensed UI framework from Inferno's creator that compiles React-style hooks, Suspense, and actions to direct DOM code. No virtual DOM, no rules of hooks, no hand-maintained dependency arrays. Here is what shipped, the benchmark grid, and what it means for teams and AI agents.

## Gemini API Managed Agents: 3.6 Flash, hooks, and more

DevFeed: [Gemini API Managed Agents: 3.6 Flash, hooks, and more](<https://devfeed.tech/articles/gemini-api-managed-agents-3-6-flash-hooks-and-more-89329.md>)

Original publisher: [Read original article](<https://blog.google/innovation-and-ai/technology/developers-tools/expanding-managed-agents-gemini-api-3-6-flash-hooks/>)

Author: Mariano Cocirio

Published: 2026-07-28T16:00:00Z

Content type: release

Language: en

Sources: [Developer tools](<https://devfeed.tech/sources/developer-tools.md>)

Topics: [hosted-agents](<https://devfeed.tech/topics/hosted-agents.md>), [hooks](<https://devfeed.tech/topics/hooks.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-api](<https://devfeed.tech/tags/gemini-api.md>), [hooks](<https://devfeed.tech/tags/hooks.md>), [managed](<https://devfeed.tech/tags/managed.md>), [none](<https://devfeed.tech/tags/none.md>), [triggers](<https://devfeed.tech/tags/triggers.md>)

### AI overview

Google describes updates to Managed Agents in the Gemini Interactions API: Gemini 3.6 Flash is the default, environment hooks can run scripts around tool calls, and managed agents gain free-tier access, token budget limits, scheduled triggers, and sandbox management through the Environments API.

### Source excerpt

Managed Agents Gemini 3.6 Flash, Hooks and Triggers

## Scheduling Claude Code for Nightly Repository Maintenance

DevFeed: [Scheduling Claude Code for Nightly Repository Maintenance](<https://devfeed.tech/articles/claude-code-can-maintain-your-repo-28977.md>)

Original publisher: [Read original article](<https://codingwithroby.substack.com/p/claude-code-can-maintain-your-repo>)

Author: Eric Roby

Published: 2026-07-28T12:03:08Z

Content type: tutorial

Language: en

Sources: [Eric Roby](<https://devfeed.tech/sources/eric-roby.md>)

Topics: [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Security](<https://devfeed.tech/topics/security.md>), [Refactoring](<https://devfeed.tech/topics/refactoring.md>), [Continuous integration](<https://devfeed.tech/topics/continuous-integration.md>), [hooks](<https://devfeed.tech/topics/hooks.md>), [Code](<https://devfeed.tech/topics/code.md>)

Tags: [automated](<https://devfeed.tech/tags/automated.md>), [ci](<https://devfeed.tech/tags/ci.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [github-action](<https://devfeed.tech/tags/github-action.md>), [hooks](<https://devfeed.tech/tags/hooks.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [refactor](<https://devfeed.tech/tags/refactor.md>), [repo](<https://devfeed.tech/tags/repo.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

The article explains how to schedule Claude Code in headless mode for recurring repository maintenance. It recommends focused jobs for security sweeps, refactoring scans, and enhancement reviews, using structured JSON output and the --bare option for consistent scripted runs.

### Source excerpt

How to schedule headless runs for nightly security sweeps, refactor scans, and enhancement ideas

## How to Stop Claude from Saying 'Load-Bearing'

DevFeed: [How to Stop Claude from Saying 'Load-Bearing'](<https://devfeed.tech/articles/how-to-stop-claude-from-saying-load-bearing-56319.md>)

Original publisher: [Read original article](<https://www.developersdigest.tech/blog/stop-claude-saying-load-bearing>)

Author: Developers Digest

Published: 2026-07-14T00:00:00Z

Content type: article

Language: en

Sources: [Developers Digest](<https://devfeed.tech/sources/developers-digest.md>)

Topics: [Claude](<https://devfeed.tech/topics/claude.md>), [hooks](<https://devfeed.tech/topics/hooks.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [claude](<https://devfeed.tech/tags/claude.md>), [developers](<https://devfeed.tech/tags/developers.md>), [discussion](<https://devfeed.tech/tags/discussion.md>), [hacker-news](<https://devfeed.tech/tags/hacker-news.md>), [hooks](<https://devfeed.tech/tags/hooks.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llms](<https://devfeed.tech/tags/llms.md>), [news](<https://devfeed.tech/tags/news.md>)

### AI overview

A Hacker News discussion examines repetitive vocabulary in Claude and the hooks, filters, and other coping mechanisms developers use to address it.

### Source excerpt

A Hacker News discussion blows up over LLM vocabulary quirks, with developers sharing hooks, filters, and coping mechanisms for repetitive Claude-isms.

## Inside the Git Hooks: Tagging Every AI Agent Commit (Part 3)

DevFeed: [Inside the Git Hooks: Tagging Every AI Agent Commit (Part 3)](<https://devfeed.tech/articles/inside-the-git-hooks-tagging-every-ai-agent-commit-part-3-25424.md>)

Original publisher: [Read original article](<https://jonnyzzz.com/blog/2026/06/26/inside-the-git-hooks-for-ai-agents/>)

Author: Eugene Petrenko

Published: 2026-06-26T00:00:00Z

Content type: tutorial

Language: en

Sources: [Eugene Petrenko](<https://devfeed.tech/sources/eugene-petrenko.md>)

Topics: [hooks](<https://devfeed.tech/topics/hooks.md>), [Git](<https://devfeed.tech/topics/git.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [commit](<https://devfeed.tech/tags/commit.md>), [eugene-petrenko](<https://devfeed.tech/tags/eugene-petrenko.md>), [git](<https://devfeed.tech/tags/git.md>), [git-hooks](<https://devfeed.tech/tags/git-hooks.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [jonnyzzz](<https://devfeed.tech/tags/jonnyzzz.md>), [sandbox](<https://devfeed.tech/tags/sandbox.md>), [tag-41199d53f463](<https://devfeed.tech/tags/tag-41199d53f463.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

The hooks provide best-effort provenance from inside an AI agent's sandbox, not a security boundary; the source says a determined agent could defeat them and describes a git proxy as the stronger floor. The design stamps each commit with a session ID, aims to preserve the tag through amend, rebase and squash, and captures a restorable copy on push. To avoid breaking repository hooks, each installed hook runs the project's corresponding hook first and honors its exit code. The excerpt also notes safeguards against recursive hook lookup and worktree path differences, and says stdin must be buffered to a temporary file so it can be replayed byte-for-byte to local hooks. The text cuts off mid-implementation, so it does not establish the complete hook set or remaining details.

### Source excerpt

Part 3 -- the build for the lighter solution. How a set of git hooks stamps a session id on every commit an AI Agent makes, survives squash and rebase, and captures each push -- all best-effort, all inside the sandbox.

[Next page](<https://devfeed.tech/topics/hooks.md?cursor=WyIyMDI2LTA2LTI2VDAwOjAwOjAwKzAwOjAwIiwgIjIwZTE2OTIwLWQ3MDItNDkyZC1iZjNhLTQxNDA4MzE2ZDZmZiJd>)