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/genm/switchbot-mcp/agents-mdgit clone --depth 1 https://github.com/genm/switchbot-mcpWhat 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 | $0.00727 | $0.00727 |
| Opus 5 | $0.00364 | $0.00364 |
| Sonnet 5 | $0.00145 | $0.00145 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
switchbot-mcp AGENTS.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 2d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file defines repository-level operating rules for AI agents working in this project.
Communication
- Use English for chat interactions, repository files, and documentation by default.
General Rules
- Use Conventional Commits for commit messages in English (no non-ASCII characters). If uncertain, inspect recent commit history first.
- If a user writes
#{number}, treat it as a GitHub Issue number and useghwhen issue operations are needed. - For GitHub Actions, always use the latest major version of
actions/*. - In Codex, refer to
ai-rules/(symlink to~/.config/ai/rules) when rule context is needed.
Skills Policy
- Store Codex skills directly under
./skills/(one-level depth). - Store user-created skills directly under
./skills/(one-level depth). - Store Claude skills directly under
./skills/(one-level depth). - Treat each
SKILL.mdas a living document: update when new findings, deprecations, or version changes are confirmed. - When updating a skill, edit the chezmoi-managed source in this repository, not deployed copies like
~/.agents/skills/**or~/.config/ai/skills/**. - After changing chezmoi-managed files, run
chezmoi applyto synchronize actual files. - For skill maintenance work, following
$chezmoi-opsis recommended.
Git / Workflow Rules
- Keep workflows as git-light as possible while preserving safe repository inspection.
- Read-only Git commands such as
git status,git diff,git log, branch inspection, andgit fetchare allowed and should be used to establish repository state before mutations. - Do not create commits, push branches, open pull requests, or merge changes for review-, diagnosis-, or explanation-only tasks.
- For implementation and delivery tasks, create commits on a dedicated feature branch when needed. Pushes, pull requests, and merges require explicit user authorization or an explicitly requested delivery workflow; never push directly to the default or another protected branch.
- Exception: if chezmoi-managed source files are changed, the chezmoi workflow may require automatic
git add/commit/pushwhen necessary unless the user explicitly opts out; this exception never authorizes a direct push to the default or another protected branch. - Prefer
chezmoi apply/chezmoi updateover direct git operations for synchronization.
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.
- 2d ago First seen · 53 lines · 727 tokens per session scan A 746b25748409
switchbot-mcp AGENTS.md is an instructions file published in the GitHub repository genm/switchbot-mcp (7 stars, last pushed 9d ago), licensed ISC. It adds 727 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
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).
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.
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.
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 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
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.