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.
npx agentmods add instructions/roderik/bellwether/claude-mdgit clone --depth 1 https://github.com/roderik/bellwetherWrote 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/roderik/bellwether/claude-md)<a href="https://agentmods.dev/instructions/roderik/bellwether/claude-md"><img src="https://agentmods.dev/badge/instructions/roderik/bellwether/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 | $0.00458 | $0.00458 |
| Opus 5 | $0.00229 | $0.00229 |
| Sonnet 5 | $0.00092 | $0.00092 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
bellwether 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 3d 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.
What it actually says
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What is this?
bellwether is a CLI tool that monitors GitHub PRs — review comments and CI status. Built with incur (a framework for CLIs that work for both AI agents and humans) and @clack/prompts for interactive UI.
Commands
bun install— install dependenciesbun check— lint with oxlint (type-aware)bun run format— format with oxfmtbun test— run tests (vitest)bun test:coverage— run tests with coverage enforcementbun run build— build with zile (tsc wrapper)bun run dev— dev mode with zile (symlink-based)
Testing
Tests live in test/ mirroring the src/ structure. Coverage thresholds: lines 99%, functions 97%, branches 93%, statements 99%. Coverage excludes src/bin.ts, src/cli.ts, src/github/index.ts (entry points and re-exports), and src/commands/hook-add.ts, src/commands/hook-check.ts (hook installer/handler with stdin dependencies).
Run a single test file: bunx vitest run test/path/to/file.test.ts
Code Style
- TypeScript ESM with
"type": "module"— useimport/export, notrequire NodeNextmodule resolution — file extensions required in imports (.jsfor.tsfiles)- Formatting is handled by oxfmt, linting by oxlint — do not add eslint or prettier
- Use
incurpatterns for CLI commands (see existing commands insrc/commands/)
Publishing
Tag-triggered via GitHub Actions: git tag v0.1.0 && git push --tags. Version is auto-set from the tag. Preview packages are published on PRs via pkg-pr-new.
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.
- 3d ago First seen · 35 lines · 458 tokens per session scan A 875fd855836a
bellwether CLAUDE.md is an instructions file published in the GitHub repository roderik/bellwether (5 stars, last pushed 9d ago), licensed MIT. It adds 458 tokens to every session, about $0.0023 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
testivai-oss CLAUDE.md
Claude Code instructions for testivai/testivai-oss, covering testivai-oss — claude code guide, repo layout, package manager, common commands and architecture — how the oss lane works.
testivai-oss AGENTS.md
AGENTS.md instructions for testivai/testivai-oss, covering testivai-oss — agent guide, what this repo is, hard rules — never violate these, repo layout and package manager.
gh-watch CLAUDE.md
Claude Code instructions for justincampbell/gh-watch, covering gh-watch, architecture, key design decisions, development and testing.
invigil AGENTS.md
AGENTS.md instructions for invigil/invigil, covering agents.md — conventions for ai coding agents, build / test / lint and layout.
std-env AGENTS.md
Instructions for unjs/std-env, covering agents, project overview, maintenance, scripts and source structure.
teamcity-mcp CLAUDE.md
Instructions for Daghis/teamcity-mcp, covering claude code instructions for teamcity-mcp, project overview, development commands, testing and unit tests.