canary AGENTS.md

Repository instructions for Canary, an AI tool that turns written requirements into test code. They describe its documentation, architecture, diagrams, and project structure.

In plain words
What is it for?
Use them when working in the Canary repository, especially on documentation, diagrams, harness integration, or its self-healing testing process.
Why use it?
They give coding agents the project-specific rules and background needed to make consistent changes.

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/bop-clocktower/canary/agents-md
Clone the repo
git clone --depth 1 https://github.com/bop-clocktower/canary

Made for: Codex, OpenCode.

Per session 18,438 This file is loaded in full into every session.
When invoked 18,438 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.18438 $0.18438
Opus 5 $0.09219 $0.09219
Sonnet 5 $0.03688 $0.03688
Haiku 4.5 $0.01844 $0.01844

Measured 2d ago against content hash e9ca85fefa78, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

canary AGENTS.md scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

threshold of 10 doing it (#622). `runCapture` wraps `spawnSync`, which returns
AGENTS.md · 1,275 lines

How it starts

The opening of the file, as written. The whole thing — 1,275 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Canary Knowledge Map

Project Overview

Canary is an AI-powered test automation agent that transforms natural language requirements into high-quality, framework-aware test code. It follows strict harness engineering practices for layer isolation and architectural integrity.

Documentation

  • Wiki Home: [Home][wiki-home]
  • Architecture Deep Dive: [Architecture Deep Dive][arch-deep-dive]
  • Harness Integration: [Harness Integration][harness-int]
  • Harness + Canary Routing & Ownership: Integration Guide
  • LLM Configuration: [LLM Providers][llm-config]
  • Self-Healing Loop: [Self-Healing Loop][self-healing]
  • Main README: README.md
  • Roadmap: docs/roadmap.md
  • State: CANARY_STATE.md
  • Engineering Learnings: CANARY_LEARNINGS.md

Diagrams

Architecture and flow diagrams live as Mermaid fenced blocks inside the wiki page they document (docs/wiki/**) — never as checked-in images. The GitHub Wiki renders Mermaid natively, so the source stays diff-reviewable, versioned with the code it describes, and editable without a drawing tool.

Rules:

  • Put the diagram next to the prose it illustrates. A diagram in a separate file drifts from the text within one release.

  • Update the diagram in the same PR as the behaviour it shows. A stale diagram is worse than none: it is trusted more and checked less.

  • Diagram what exists, not what is planned. If a component is aspirational, say so in prose instead of drawing it.

  • CI renders every chart (Docs LintWiki diagrams render). The Wiki renders Mermaid natively, which means a malformed chart ships silently — the job turns that into a PR-time failure. Preview locally with:

    npx --yes @mermaid-js/mermaid-cli@11 -i docs/wiki/<Page>.md -o /tmp/out.md
    

Beware the failure mode this repo has already hit: a doc sweep once refreshed file paths to the current tree without checking whether the components they named still existed, leaving a page that looked maintained while describing a long-deleted architecture. When editing, verify described behaviour against the code, not just the paths.

Read the full file on GitHub · 1,275 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. 2d ago First seen · 1,275 lines · 18,438 tokens per session scan A e9ca85fefa78

Subscribe to this mod's changes

canary AGENTS.md is an instructions file published in the GitHub repository bop-clocktower/canary (4 stars, last pushed 3d ago), licensed MIT. It adds 18,438 tokens to every session, about $0.0922 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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 · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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

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 · 4,345 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

vercel/next.js · 7,296 tokens