What is agent-readiness copilot-instructions.md?

Project instructions for Agent Readiness, a deterministic Python command-line scanner that checks whether a repository is prepared for AI coding agents. It analyzes files locally without network access or language-model calls.

Use it when adding or changing scanner checks, writing tests first, or preserving the project's architecture and excluded-scope rules.

It sets boundaries that keep the scanner predictable, dependency-free at runtime, and focused on repository checks.

agent-readiness copilot-instructions.md — Instructions file by chevy155

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/copilot-instructions

Clone the repo

git clone --depth 1 https://github.com/chevy155/agent-readiness

Made for: GitHub Copilot.

Per session 634 This file is loaded in full into every session.

When invoked 634 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.

Model	Per session	Once invoked
Fable 5	$0.00634	$0.00634
Opus 5	$0.00317	$0.00317
Sonnet 5	$0.00127	$0.00127
Haiku 4.5	$0.00063	$0.00063

Measured 2d ago against content hash df03e08b6011, 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 copilot-instructions.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.

.github/copilot-instructions.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions — agent-readiness

Instructions for GitHub Copilot, Cursor, Claude Code, and all AI coding agents in this repo.

Project

agent-readiness is the Agent Readiness Scanner — a deterministic Python CLI that checks whether a repository is ready for AI coding agents. It has zero runtime dependencies and makes no network or LLM calls.

Hard Constraints

Keep v0 deterministic. The core scanner (checks.py) must remain pure file-system analysis. Do not add LLM calls, network requests, or probabilistic logic to the check functions.

Keep zero runtime dependencies. agent_readiness/ must import from the standard library only. Dev dependencies (pytest) are fine. Production dependencies are not.

Tests first. Before adding a new check or feature, write a failing test in tests/. Use tmp_path pytest fixture to create isolated test repos.

Do not expand scope. Do not add: SaaS, auth, dashboards, billing, webhooks, telemetry, GitHub App, Slack integration, or any external API. These are future scope items.

Architecture

agent_readiness/
  checks.py    — 17 deterministic check functions, each returns CheckResult TypedDict
  scoring.py   — compute_score(), get_tier(), get_recommendations() — pure math
  report.py    — render_terminal(), render_json(), render_markdown() — pure rendering
  templates.py — generate_agents_md(), generate_copilot_instructions() — file generation
  cli.py       — argparse CLI entry point, calls the above modules

Each module has a single responsibility. Keep it that way.

Style

Python ≥ 3.9, type-annotated with from __future__ import annotations
TypedDict for structured data (not dataclasses)
Functions return values; they do not mutate shared state
ANSI color codes in terminal output only — use TIER_COLORS / RESET from scoring.py
No print() in library modules (checks.py, scoring.py, report.py, templates.py)
CLI output goes through cli.py only

Read the full file on GitHub · 85 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.

2d ago First seen · 85 lines · 634 tokens per session scan A df03e08b6011

Subscribe to this mod's changes

agent-readiness copilot-instructions.md is an instructions file published in the GitHub repository chevy155/agent-readiness (4 stars, last pushed 3mo ago), licensed MIT. It adds 634 tokens to every session, about $0.0032 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 agent-readiness ai-agents claude-code codex coding-agents cursor

agent-readiness copilot-instructions.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Copilot Instructions — agent-readiness

Project

Hard Constraints

Architecture

Style

What this file has done since we first saw it

Other instructions, from other repositories

meta-llm-charter CLAUDE.md

awesome-reviewers CLAUDE.md

code-context AGENTS.md

gtm-cheat-codes CLAUDE.md

Stata-CLI AGENTS.md

waybill AGENTS.md