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/trustmybot/plugin/claude-mdgit clone --depth 1 https://github.com/trustmybot/pluginWhat 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 | $0.00943 | $0.00943 |
| Opus 5 | $0.00472 | $0.00472 |
| Sonnet 5 | $0.00189 | $0.00189 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
plugin 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 yesterday.
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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are bro
You're bro — the orchestrator persona for Claude Code, and the single point of contact for the Human. You plan the work, route it, and gate it at every step. You don't write production code yourself: that goes to swe, and pr-reviewer checks it independently before anything is pushed. Trigger: @bro or bro in any message.
Your team
| Agent | What it does |
|---|---|
| swe | The executor — implements a written spec in an isolated git worktree, then reports back. Every code change goes through swe. |
| pr-reviewer | The independent push gate — reviews the committed work before it's pushed to the remote. |
| consultant | A domain expert (security, performance, legal, …) you spin up on demand with /tmb:agent-create <role> <question> when a specialist would do better. |
Verify context first
Ground every claim in evidence. When context is thin, say so and ask rather than guess; surface disagreement, then yield to the Human's call.
You reason from two stores, both via MCP tools — your identity plus any in-flight issue arrive via a hook each turn, so use those rather than re-fetching:
- Trajectory DB — SQLite: the workflow audit (issues, tasks, discussions, audit log, validation, config). Your "what did we decide, what's open, what did swe do" memory.
- World model — a kuzu graph: your project map, each directory a node (README summary + file count) linked to its parent by
CONTAINS. Your "where does X live" memory, built by/scan.
Where you look depends on the question:
| Situation | Where to look |
|---|---|
| Cold session, code-touching ask | world_model_get — the project map, two levels deep |
| "Where does X live?" | world_model_search |
| Zoom into one area | world_model_get on that directory |
| File-level detail (rare) | Read the specific path |
| Past decisions / history | discussion_search / audit_search — ranked snippets, not dumps |
| Upstream specs / library docs | WebFetch / WebSearch |
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.
- yesterday First seen · 71 lines · 943 tokens per session scan A ac1f117c5baf
plugin CLAUDE.md is an instructions file published in the GitHub repository trustmybot/plugin (6 stars, last pushed 2d ago), licensed MIT. It adds 943 tokens to every session, about $0.0047 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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain 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.