# How ExecPlans help coding agents work on complex tasks

DevFeed: [How ExecPlans help coding agents work on complex tasks](<https://devfeed.tech/articles/execplans-how-to-get-your-coding-agent-to-run-for-hours-25244.md>)

Original publisher: [Read original article](<https://kau.sh/blog/exec-plans/>)

Author: Kaushik Gopal

Published: 2025-10-13T01:01:48Z

Content type: tutorial

Language: en

Sources: [Kaushik Gopal's Site](<https://devfeed.tech/sources/kaushik-gopal-s-site.md>)

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [codex](<https://devfeed.tech/topics/codex.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>), [coding](<https://devfeed.tech/topics/coding.md>), [cursor](<https://devfeed.tech/topics/cursor.md>)

Tags: [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [codex](<https://devfeed.tech/tags/codex.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [feature](<https://devfeed.tech/tags/feature.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [update](<https://devfeed.tech/tags/update.md>)

## AI overview

This article explains how the author uses ExecPlans--structured planning documents inspired by Aaron Friel's PLANS.md--to guide coding agents through complex tasks. It recommends storing plans in project directories, configuring agents through AGENTS.md, and using temporary gitignored plans. The author reports improved results across several pull requests, while noting that larger projects still need further testing.

## Source excerpt

I've long maintained that the biggest unlock with AI coding agents is the planning step. In my previous post, I describe how I use a .ai/plans directory and ask the agent to diligently write down its tasks before and during execution. Most coding agents now include this as a feature. Cursor, for example, introduced it as an explicit feature recently. While that all felt validating, on a plane ride home I watched OpenAI's DevDay. One of the most valuable sessions was Shipping with Codex. Aaron Friel -- credited with record-long sessions and token output -- walked through his process and the idea of "ExecPlans." It felt similar at first, but I quickly realized this was some god-level planning. He said OpenAI would release his PLANS.md soon, but I couldn't wait. On that flight, with janky wifi, I rebuilt what I could from the talk and grew my baby plan into something more mature -- and I was already seeing better results. I pinged Aaron on BlueSky for the full doc, and he very kindly shared the PR that's about to get merged with detailed information. My god, this thing is a work of art. Aaron clearly spent a lot of time honing it. I've tried it on two PRs so far, and it's working fantastically. I still need to put it through its paces on some larger work projects, but I feel comfortable preemptively calling it the gold standard for planning. I've made a few small tactical tweaks to how I use it: I instruct the agent to write plans to .ai/plans (works across coding agents) In my AGENTS.md I tell agents to put temporary plans in .ai/plans/tmp (which I've gitignored) I keep the master PLANS.md Aaron shared at @.ai/plans/PLANS.md This is really a big unlock, folks. Try it now. The latest PLANS.md can be found in Aaron's PR. Use it as a template in your .ai/plans folder. Then instruct your agent via AGENTS.md to always write an ExecPlan when working on complex tasks. I highly recommend you go watch Aaron's part of the talk Shipping with Codex. I'll update this post once it's m