Borrowing it
Nothing to install: this file belongs to thomas-powers-jr/cadence. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/thomas-powers-jr/cadence/main/CLAUDE.mdgit clone --depth 1 https://github.com/thomas-powers-jr/cadenceWrote 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.
[](https://agentmods.dev/instructions/thomas-powers-jr/cadence/claude-md)<a href="https://agentmods.dev/instructions/thomas-powers-jr/cadence/claude-md"><img src="https://agentmods.dev/badge/instructions/thomas-powers-jr/cadence/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/thomas-powers-jr/cadence/claude-md"><img src="https://agentmods.dev/badge/instructions/thomas-powers-jr/cadence/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.08333 | $0.08333 |
| Opus 5 | $0.04167 | $0.04167 |
| Sonnet 5 | $0.01667 | $0.01667 |
| Haiku 4.5 | $0.00833 | $0.00833 |
Grade B, and why
cadence CLAUDE.md scanned grade B with 2 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 today.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
mid-turn (`~/.claude/settings.json`: `model: sonnet` + `advisorModel: opus` + Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
`child_process.spawn` of `npx` needs `shell: true` on win32; path How it starts
The opening of the file, as written. The whole thing — 558 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Operating manual for AI agents working in this repository. Read it before touching anything. Most conventions here are backed by an enforcement layer — a git hook, a CI job, a doc-content test, or a CADENCE gate — so violating them doesn't just annoy the operator, it fails the build. Where a rule has no mechanical enforcement, that is stated, and the operator's review is the backstop.
What this repo is
CADENCE is a draft/build/settle framework for AI-assisted development with
configurable quality gates. It is a meta-tool: it scaffolds and runs the
DRAFT→BUILD→SETTLE loop on consumer projects, and uses that same loop on
itself. The .cadence/ directory at the repo root is not example data —
it is the live state of CADENCE planning CADENCE.
The project's core thesis: an AI agent's self-report of "done" is not proof. Gates re-derive completion from real state (tests, diffs, task records) and refuse to settle when the evidence doesn't back the claim. You are an AI agent working inside the tool built to distrust AI agents — every rule in this manual follows from that thesis, and most of the failure modes listed at the bottom are some flavor of violating it.
Current version: 1.67.0 across all five published packages (lockstep).
Do not reconstruct release history from memory or from this file — it lives
in packages/*/CHANGELOG.md, GitHub Releases,
git log, and .cadence/phases/*/. When a release bumps
packages/core/package.json, the version line above must be updated in
the same commit (the doc-sync gate below aborts the commit otherwise, and CI
re-asserts it on every OS).
Read these before working (in order)
CONTEXT.md— the canonical vocabulary and its forbidden aliases. Read it before exploring code; reviews, docs, and doc tests are written against this glossary.DESIGN.md— locked decisions (D1–D12, §12–§14), anti-goals, and deliberately rejected alternatives. LOCKED decisions are not open for relitigation; if a task seems to require reversing one, stop and say so instead of quietly doing it.docs/concepts.md— the loop, profiles × tiers, the full gate matrix.docs/reference/commands.md,docs/reference/config.md— CLI + config.AGENTS.md+docs/agents/— issue tracker (GitHub viaghCLI), triage labels (needs-triage,needs-info,ready-for-agent,ready-for-human,wontfix), domain-doc protocol.
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.
- today Changed 7b2ab88b5b98
- 8d ago First seen · 558 lines · 8,333 tokens per session scan B 6cb0f188bc61
cadence CLAUDE.md is an instructions file published in the GitHub repository thomas-powers-jr/cadence (2 stars, last pushed today), licensed MIT. It adds 8,333 tokens to every session, about $0.0417 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
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.