agentmods.dev

cadence: Instructions file for Claude Code

CLAUDE.md

cadence CLAUDE.md is an instructions file for Claude Code from thomas-powers-jr/cadence. It costs 8,504 tokens per session, scanned B, original, MIT.

Repository instructions for CADENCE, a framework that runs draft, build, and settle stages with quality checks for AI-assisted development.

In plain words
What is it for?
They are for working safely in the CADENCE repository, understanding its structure, following its commands and conventions, and avoiding failures in hooks, CI, documentation checks, or quality gates.
Why use it?
They explain the rules and checks an AI agent must follow so that claims of completion are supported by tests, code changes, and task records.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is thomas-powers-jr/cadence's own configuration. It tells Claude Code how to work on cadence itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cadence configures →

not rated 2repo changed 7d ago B scan 8,504 tokens original MIT
View source ↗ thomas-powers-jr/cadence thomas-powers-jr.github.io
Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/thomas-powers-jr/cadence/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/thomas-powers-jr/cadence

Made for: Claude Code.

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.

agentmods badge for cadence CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/thomas-powers-jr/cadence/claude-md/github.svg)](https://agentmods.dev/instructions/thomas-powers-jr/cadence/claude-md)
Your own site
<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.

agentmods 80×15 button for cadence CLAUDE.md

Your own site · 80×15
<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>
Per session 8,504 This file is loaded in full into every session.
When invoked 8,504 The same file — it is already loaded in full.
Security scan B 2 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.08504 $0.08504
Opus 5.5 $0.03402 $0.03402
Sonnet 5.5 $0.01701 $0.01701
Haiku 4.5 $0.00850 $0.00850

Measured 7d ago against content hash 7048c4e1381d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 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.

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
CLAUDE.md · 568 lines

How it starts

The opening of the file, as written. The whole thing — 568 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: 1.73.0 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)

  1. CONTEXT.md — the canonical vocabulary and its forbidden aliases. Read it before exploring code; reviews, docs, and doc tests are written against this glossary.
  2. 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.
  3. docs/concepts.md — the loop, profiles × tiers, the full gate matrix.
  4. docs/reference/commands.md, docs/reference/config.md — CLI + config.
  5. AGENTS.md + docs/agents/ — issue tracker (GitHub via gh CLI), triage labels (needs-triage, needs-info, ready-for-agent, ready-for-human, wontfix), domain-doc protocol.

Read the full file on GitHub · 568 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. 7d ago Changed 7048c4e1381d
  2. 8d ago Changed 5d46e199a1a9
  3. 14d ago Changed 943520b804b7
  4. 15d ago Changed · +1 lines · +16 tokens per session 0e3221297a3c
  5. 27d ago Changed · +8 lines · +131 tokens per session c9876d247cec
  6. 28d ago Changed 806092cc9adf
  7. 1mo ago Changed · +1 lines · +24 tokens per session 76b3b1caac51
  8. 1mo ago Changed 5f85a0fc4307
  9. 1mo ago Changed 293b2e005a79
  10. 1mo ago First seen · 558 lines · 8,333 tokens per session scan B fa3045e39db7

Subscribe to this mod's changes

cadence CLAUDE.md is an instructions file published in the GitHub repository thomas-powers-jr/cadence (2 stars, last pushed yesterday), licensed MIT. It adds 8,504 tokens to every session, about $0.0340 per session on Opus 5.5. 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.

agentic-aiaiai-agentsclicode-qualitydeveloper-tools
Related

cadence CLAUDE.md compared with instructions from other repositories

cadence CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cadence CLAUDE.mdthomas-powers-jr/cadenceInstructions file2yesterdayMITB8,504Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode