planning-with-files: Instructions file for Codex

AGENTS.md

planning-with-files AGENTS.md is an instructions file for Codex, OpenCode from OthmanAdi/planning-with-files. It costs 1,090 tokens per session, scanned A, original, MIT.

A project instruction file that tells coding agents how to handle commits, releases, version changes, changelog entries, and issue or pull-request communication.

In plain words
What is it for?
It helps agents prepare releases, update versions and changelogs, review issues and pull requests, and follow the repository’s commit and publishing rules.
Why use it?
It gives every agent the same repository rules, reducing mistakes such as lost contributor credit, incorrect commit formats, or skipped release checks.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions subagents; mentions AGENTS.md.

This is OthmanAdi/planning-with-files's own configuration. It tells Codex and OpenCode how to work on planning-with-files itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything planning-with-files configures →

About the project

OthmanAdi/planning-with-files is a planning system that stores an AI coding agent's task plan, findings, and progress in project files so the work can be recovered after context resets, crashes, or compaction. It is for long-running coding tasks across many agent tools, including Claude Code, Codex CLI, and Cursor. The catalogue entries are the project's commands, hooks, skills, plugin, and instruction for maintaining those planning files.

OthmanAdi/planning-with-files · 27,535 stars · on GitHub · gilded-laurel-c7nj.here.now

Reuse

Borrowing it

Nothing to install: this file belongs to OthmanAdi/planning-with-files. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/OthmanAdi/planning-with-files/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/OthmanAdi/planning-with-files

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for planning-with-files AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/othmanadi/planning-with-files/agents-md/github.svg)](https://agentmods.dev/instructions/othmanadi/planning-with-files/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/othmanadi/planning-with-files/agents-md"><img src="https://agentmods.dev/badge/instructions/othmanadi/planning-with-files/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for planning-with-files AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/othmanadi/planning-with-files/agents-md"><img src="https://agentmods.dev/badge/instructions/othmanadi/planning-with-files/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,090 This file is loaded in full into every session.
When invoked 1,090 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.01090 $0.01090
Opus 5.5 $0.00436 $0.00436
Sonnet 5.5 $0.00218 $0.00218
Haiku 4.5 $0.00109 $0.00109

Measured 1mo ago against content hash 651067324f17, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

planning-with-files AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 29 lines

How it starts

The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md, planning-with-files maintainer rules

For any agent doing releases, merges or issue work in this repository. The code and scripts/ are discoverable; this file holds the decisions that are not.

Authorship

  • Contributor commits keep the contributor as Author:. Merge with git fetch origin pull/N/head:pr-N && git cherry-pick <sha> or gh pr merge --rebase. Never git merge --squash a contributor PR: it reassigns their commit to whoever runs the local commit, which happened once in the v2.40.1 cycle. Squash only your own WIP before pushing.
  • Release and maintenance commits are authored by OthmanAdi alone, Conventional Commits (fix:, feat:, release:, docs:), no Co-Authored-By. Contributors are credited in the CHANGELOG ### Thanks section and in CONTRIBUTORS.md, never in trailers.
  • No --no-verify. No force push to master except tag ref updates and history corrections Adi explicitly authorised.

Release flow

  1. Read the issue and the PR in full (gh issue view N, gh pr view N). Reproduce the claim against the code. Audit the diff for supply-chain vectors (new dependencies, install scripts, bin shims, files in the install path). Comment on the issue the moment it is confirmed, with the planned fix; the closing comment comes after shipping. Never batch all communication to the end.
  2. python -m pytest tests/ -q is green before and after the merge.
  3. Merge the contributor commits as above, then one release commit on top: CHANGELOG entry, CONTRIBUTORS.md (entry, total count, date), README version badge and releases table row, version bump.
  4. Bump with python scripts/bump-version.py X.Y.Z (--dry-run first), never by hand. tests/test_skill_md_version_parity.py defines the parity set (19 tracked files plus the gitignored clawhub-upload/SKILL.md when present); the script and the test are the source of truth, not any list in prose. Deliberately lagging: .continue and .gemini (bump only on an explicit scope decision), .kiro (own -kiro scheme), .pi/.../SKILL.md (no version field; the Pi version is its package.json, which is in the set). The bundled Pi extension's own package.json moves only when that extension changed.
  5. Tag vX.Y.Z on the release commit, push master and the tag, then gh release create vX.Y.Z --title "vX.Y.Z - <short description>" --notes "<what changed, then Thanks>".
  6. Distribution is manual after every release. ClawHub: python scripts/build-clawhub-upload.py, then python scripts/build-clawhub-upload.py --verify (the staged folder must match the tracked inventory), then upload the whole clawhub-upload/ folder at clawhub.io (its SSL certificate may be expired; proceed through the warning). npm: npm publish from .pi/skills/planning-with-files/ (the unscoped package planning-with-files, Adi's account; the abandoned @tomxprime/planning-with-files and pi-planning-with-files are never touched). skills.sh and npx skills pull master on their own; the Anthropic marketplace reflects the ClawHub upload.
  7. Comment on the PR and the issue (contributor's @handle, the version that fixes it, root cause and mechanism, "you are in CONTRIBUTORS.md" when true, the commit SHA so it auto-links), then close what GitHub did not close.

Read the full file on GitHub · 29 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago Changed · -133 lines · -1,146 tokens per session 651067324f17
  2. 1mo ago Changed · +42 tokens per session c6aeaa9d7fec
  3. 1mo ago First seen · 162 lines · 2,194 tokens per session scan A cae4bfdd4e06

Subscribe to this mod's changes

planning-with-files AGENTS.md is an instructions file published in the GitHub repository OthmanAdi/planning-with-files (27,535 stars, last pushed 2d ago), licensed MIT. It adds 1,090 tokens to every session, about $0.0044 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,649 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,257 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,159 tokens