Borrowing it
Nothing to install: this file belongs to chipmates/cctap. 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/chipmates/cctap/main/CLAUDE.mdgit clone --depth 1 https://github.com/chipmates/cctapWrote 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/chipmates/cctap/claude-md)<a href="https://agentmods.dev/instructions/chipmates/cctap/claude-md"><img src="https://agentmods.dev/badge/instructions/chipmates/cctap/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/chipmates/cctap/claude-md"><img src="https://agentmods.dev/badge/instructions/chipmates/cctap/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 | $0.00828 | $0.00828 |
| Opus 5.5 | $0.00331 | $0.00331 |
| Sonnet 5.5 | $0.00166 | $0.00166 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
cctap CLAUDE.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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - cctap
Guidance for Claude Code and any other coding agent working in this repository. Contribution guidelines are in CONTRIBUTING.md.
What this is
cctap is a terminal-native attention router for parallel Claude Code sessions. It watches sessions through hooks, keeps one state model in a small local daemon, renders a glyph strip, and jumps you to the session that needs you.
Hard rules
- Zero runtime dependencies.
package.jsondependenciesstays{}forever. Runtime imports arenode:*builtins or relative paths, nothing else. - Hooks must never disturb Claude Code. The forwarder always exits 0, never writes to
stdout, and self-terminates inside 100 ms. See invariants I1 to I3 in
spec/CONTRACTS.md. On several hook events, stdout becomes model context and exit 2 blocks the action, so both are absolute. - Never inject input into a Claude session. Jumping there is the approve flow. The decision stays with the human.
- Local only. A unix socket under
~/.cctap/, directory 0700, files 0600. No TCP, no telemetry, no network egress of any kind. - The state machine is a pure reducer. No clock reads, no I/O, no randomness. Time enters through an event timestamp or an explicit sweep call.
- TypeScript strict, Node 22 or newer, pnpm.
The spec is normative
spec/CONTRACTS.md: socket protocol, wire shapes, invariants I1 to I19, test requirements.spec/transitions.md: the state machine, single source of truth for the reducer.spec/fixtures/*.json: acceptance fixtures, consumed verbatim by the test suite.
If code and spec disagree, the spec wins. Change the spec deliberately, in its own commit.
Test hygiene, not negotiable
- Every test and every manual run sets
CCTAP_DIRto a temp directory. Never the real~/.cctap. - Anything touching Claude Code settings sets
CCTAP_CLAUDE_SETTINGS. Never the real~/.claude. - Every test file sets
CCTAP_NOTIFY=offandCCTAP_NO_EXEC=1at import time, andtempEnv()passes both to child processes. No test may fire a desktop banner, send an Apple event, or pop an Automation consent dialog. tests/invariants.test.tsenforces the two rules above and will fail if they are weakened.- State machine changes need a row in
tests/coverage.test.ts, which walks the whole event table.
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.
- 2mo ago First seen · 72 lines · 828 tokens per session scan A 22a200540ce0
cctap CLAUDE.md is an instructions file published in the GitHub repository chipmates/cctap (3 stars, last pushed 17d ago), licensed MIT. It adds 828 tokens to every session, about $0.0033 per session on Opus 5.5. 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.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.