Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/eestevanell/codex-planning-kit/agents-mdgit clone --depth 1 https://github.com/EEstevanell/codex-planning-kitWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01208 | $0.01208 |
| Opus 5 | $0.00604 | $0.00604 |
| Sonnet 5 | $0.00242 | $0.00242 |
| Haiku 4.5 | $0.00121 | $0.00121 |
Grade A, and why
codex-planning-kit 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guidance for Codex Agents
This repository is a template for a Codex workflow based on issue cards and ExecPlans. Before using it in a real project, replace all TEMPLATE placeholders with repo-specific details.
Core expectations
- Align proposed solutions with the existing architecture and coding conventions observed in the codebase.
- Prioritize best practices, code clarity, and long-term maintainability with every change.
- Optimize for small blast radius and minimal behavioral change (risk), not small line-count. Avoid unrelated "drive-by" edits outside the code path you are already touching.
- Avoid overengineering and speculative abstractions; pick the simplest design that meets the requirement without adding clutter.
- Never delete directories or files unless the user explicitly asks for that deletion in the same turn. Never delete unrelated files. If cleanup is needed, list candidates and ask first.
- Use TDD (red-green-refactor) for behavioral changes: start with a focused failing test, implement until green, then refactor. If automated tests are impractical, document why and provide a concrete manual verification path.
- Local refactors (within the touched file/module, no public API changes) are encouraged; keep them scoped, mechanical, and reviewable.
- Significant refactors (file moves, new-file extractions, cross-cutting redesigns, or public API changes) require explicit approval in the issue card or ExecPlan before implementation; list affected files and intended invariants.
- Ground every decision in prior art. Prefer repo sources (issue cards, ExecPlans, docs, README); external sources are citations only. Restate the relevant rule/constraint in the card or plan so implementation stays self-contained.
- When multiple valid approaches exist, prefer the one with the best maintainability-to-risk ratio; do not avoid a good refactor solely to minimize diff size.
- Do not implement fallback behavior that masks invalid states; fail explicitly with clear errors and block unsafe flows.
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.
- 2d ago First seen · 68 lines · 1,208 tokens per session scan A 4c4abd09b570
codex-planning-kit AGENTS.md is an instructions file published in the GitHub repository EEstevanell/codex-planning-kit (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 1,208 tokens to every session, about $0.0060 per session on Opus 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 2026-08-31.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.