Borrowing it
Nothing to install: this file belongs to alwh1te/agent-semaphore. 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/alwh1te/agent-semaphore/main/CLAUDE.mdgit clone --depth 1 https://github.com/alwh1te/agent-semaphoreWrote 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/alwh1te/agent-semaphore/claude-md)<a href="https://agentmods.dev/instructions/alwh1te/agent-semaphore/claude-md"><img src="https://agentmods.dev/badge/instructions/alwh1te/agent-semaphore/claude-md.svg" alt="Measured on agentmods" 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 | $0.00716 | $0.00716 |
| Opus 5 | $0.00358 | $0.00358 |
| Sonnet 5 | $0.00143 | $0.00143 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
agent-semaphore 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 6d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-semaphore — repository rules
A coordination layer for parallel coding agents: claims/leases + enforcement hooks +
conflict radar + a serialized integration queue. Architecture:
docs/adr/ADR-001-architecture.md. Research it is built on: docs/00-research.md.
Hard rules
src/agent_semaphore/hooks/pretooluse.pyis stdlib-only. It must never import the package: it is vendored outside the tree with a resolved shebang and runs on every write of every agent, so it lives on a latency budget (p95 < 100 ms, gated bybench/hook_latency.py) instead of on dependencies. It is also strictly read-only against the database — telemetry goes to an append-only spool that a later CLI or MCP call ingests.- Never name a file
*token*(tokens.py,fencing_tokens.md, …). Agent tooling commonly denies reads on that pattern, and a file nobody can open is worse than a badly named one. The vocabulary here isepoch,fence,fencing. - Any multi-step invariant runs inside
BEGIN IMMEDIATE. Grant is one transaction: lazy expiry → overlap check →fence + 1→ insert, so there is no TOCTOU window by construction. Keep transactions under ~5 ms and do all git work outside them. - Exit codes are a contract:
0ok/free,3held/conflict/bounced,2usage,1internal error. Scripts and the pre-commit hook distinguish "coordination said no" from "the tool broke", so never collapse3into1.
Stack and commands
- Python 3.12+ (pinned 3.13) with uv; a single runtime dependency,
mcp. - Tests:
uv run pytest -q. Lint/format:uv run ruff check .anduv run ruff format .. - CLI:
uv run asem --help; install system-wide withuv tool install -e .. - Benchmarks:
bench/runner.py(scripted),bench/llm_runner.py(live agents, costs money),bench/hook_latency.py(the latency gate).
Conventions
- Commits are milestone-shaped (
M5: integration queue — ...) or describe the finding that motivated the change. State what broke and why the fix is shaped the way it is. - Feature branches come off
main; the queue lands intoasem/integration. - The repository dogfoods itself: the semaphore hook is installed here and the mode lives
in
.agent-semaphore.toml. If you are an agent working in this repo, claim your scope before sustained edits and read the deny text when a write is refused. - Committed wiring (
.claude/settings.json,.mcp.json) must stay host-portable:$HOME-relative hook paths and a bareasemcommand, never one machine's absolute paths.tests/test_installer.pyenforces this. - Tests must be hermetic against the host environment (git identity, git version). Two
portability bugs reached
mainbecause they were not.
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.
- 6d ago First seen · 46 lines · 716 tokens per session scan A fe5da27be7c9
agent-semaphore CLAUDE.md is an instructions file published in the GitHub repository alwh1te/agent-semaphore (0 stars, last pushed 19d ago), licensed MIT. It adds 716 tokens to every session, about $0.0036 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.
Other instructions, from other repositories
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).
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.
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.