Guiding work on the agent-context-doctor codebase, enforcing its restrictions, and documenting the commands agents should run before submitting changes.

It gives coding agents the project context and boundaries they need before changing code. It also lists checks to run so formatting, types, and linting problems are caught before finishing.

How alipajand/agent-context-doctor configures Codex and OpenCode

Q: What is agent-context-doctor AGENTS.md?

A repository instruction file for agent-context-doctor, a TypeScript command-line tool that checks agent instruction files for quality, safety, contradictions, and outdated commands. It records the project's rules, technologies, and required checks.

Reuse

Borrowing it

Nothing to install: this file belongs to alipajand/agent-context-doctor. 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/alipajand/agent-context-doctor/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/alipajand/agent-context-doctor

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/alipajand/agent-context-doctor/agents-md.svg)](https://agentmods.dev/instructions/alipajand/agent-context-doctor/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/alipajand/agent-context-doctor/agents-md"><img src="https://agentmods.dev/badge/instructions/alipajand/agent-context-doctor/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 572 This file is loaded in full into every session.

When invoked 572 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.

Model	Per session	Once invoked
Fable 5.1	$0.00572	$0.00572
Opus 5	$0.00286	$0.00286
Sonnet 5	$0.00114	$0.00114
Haiku 4.5	$0.00057	$0.00057

Measured 7d ago against content hash 6c6f5e203881, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agent-context-doctor 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 7d 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 · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS — agent-context-doctor

This is a TypeScript Node.js CLI project. You are an implementation agent.

What this project is

agent-context-doctor (acd) is a deterministic CLI that audits agent instruction files for quality, safety, contradictions, and stale commands. It is not an AI product.

Absolute constraints

Do not do any of the following without explicit approval:

Add LLM or AI API calls of any kind
Add telemetry, analytics, or any outbound network calls
Add authentication or credential handling
Build a web server, web app, or browser UI
Change the binary name (acd) or existing command names (audit, list)
Modify .acdrc schema in a breaking way
Change the AuditResult JSON shape in a backward-incompatible way
Write to any file outside the audited repo path (only --output writes are allowed)
Add dependencies that make external network requests

Tech stack

TypeScript, ESM, Node.js ≥ 18
pnpm
commander, fast-glob, zod, picocolors
vitest for tests, tsx for dev, prettier for formatting

Commands to run before finishing

pnpm format:check   # formatting
pnpm typecheck      # TypeScript
pnpm lint           # also TypeScript (same as typecheck)
pnpm test           # vitest — all tests must pass
pnpm build          # tsc compilation to dist/

All five must pass with zero errors before you consider work complete.

Code conventions

All source files live under src/; tests under tests/
Each audit check is a pure function in src/audit/checks/
Cross-file logic goes in auditRepo.ts, not in individual checks
No any types; no ts-ignore comments
Do not add comments that narrate what the code does — only explain non-obvious intent

Safe-write behavior

The only file the tool writes is the optional Markdown report via --output. Paths are resolved relative to the audited repo root. Do not add any other file-write operations without approval.

Final report

Read the full file on GitHub · 66 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.

7d ago First seen · 66 lines · 572 tokens per session scan A 6c6f5e203881

Subscribe to this mod's changes

agent-context-doctor AGENTS.md is an instructions file published in the GitHub repository alipajand/agent-context-doctor (1 stars, last pushed yesterday), licensed MIT. It adds 572 tokens to every session, about $0.0029 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.

Building agents

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.

openai/codex · 5,182 tokens

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 · 6,785 tokens

agent-context-doctor: Instructions file for Codex