agent-readiness AGENTS.md

Repository instructions for Agent Readiness, a Python command-line tool that checks whether a code repository is prepared for AI coding agents. It looks for governance files, automation, testing signals, documentation, and safety patterns.

In plain words
What is it for?
Use them when fixing eligible scanner bugs, adding tests, improving documentation or types, or making limited single-module refactors.
Why use it?
They define the project’s purpose, permitted changes, and validation expectations so work stays within the current release scope.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/chevy155/agent-readiness/agents-md
Clone the repo
git clone --depth 1 https://github.com/chevy155/agent-readiness

Made for: Codex, OpenCode.

Per session 1,365 This file is loaded in full into every session.
When invoked 1,365 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01365 $0.01365
Opus 5 $0.00682 $0.00682
Sonnet 5 $0.00273 $0.00273
Haiku 4.5 $0.00136 $0.00136

Measured 3d ago against content hash e30204b09c91, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-readiness 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 3d 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 · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — agent-readiness

Operational guidance for AI coding agents working in this repository. Applies to: Cursor, Claude Code, GitHub Copilot, Codex, and local agents.


Project Purpose

agent-readiness is the Agent Readiness Scanner — a deterministic Python CLI that checks whether a repository is ready for AI coding agents. It scans for governance files, CI configuration, test coverage signals, documentation, and safety patterns.

The product goal is a self-serve, hands-off tool. It must require no consulting, no manual intervention, and no external services to reach first value.

Current version: v0.3.0 — CLI only.

v0.2 priority is bounded: critical-failure visibility and positioning clarity only. Do not expand the product while working this release.


Allowed Changes

Agents are explicitly permitted to:

  • Fix bugs in existing check functions when a test identifies a clear failure
  • Add new tests to tests/ using the tmp_path pytest fixture
  • Improve docstrings, type annotations, and inline comments
  • Refactor within a single module without changing public function signatures
  • Fix linter warnings (ruff, pyright) without changing behavior
  • Update the README if user-facing behavior changes
  • Add new check functions to checks.py if they follow the CheckResult TypedDict contract

Forbidden Changes

Agents must not make the following changes without explicit operator approval:

  • Add any runtime dependency to pyproject.toml
  • Add network calls, HTTP requests, or socket operations of any kind
  • Add LLM API calls, model loading, or AI inference
  • Add telemetry, analytics, crash reporting, or usage tracking
  • Modify .github/workflows/test.yml (CI is operator-controlled)
  • Remove or rename the agent-scan CLI entry point
  • Change the CheckResult TypedDict structure in a breaking way
  • Add SaaS, auth, dashboard, billing, or GitHub App features
  • Expand scope to include Token Burn Firewall or Repo Red Cell Bot

Before adding any new feature, check docs/LAUNCH_LOG.md and the latest reports/OPS_REPORT_*.md. If launch feedback does not support the feature, do not build it without explicit operator approval.

Read the full file on GitHub · 171 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. 3d ago First seen · 171 lines · 1,365 tokens per session scan A e30204b09c91

Subscribe to this mod's changes

agent-readiness AGENTS.md is an instructions file published in the GitHub repository chevy155/agent-readiness (4 stars, last pushed 3mo ago), licensed MIT. It adds 1,365 tokens to every session, about $0.0068 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.