Borrowing it
Nothing to install: this file belongs to tatuke/agent-switch. 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/tatuke/agent-switch/main/AGENTS.mdgit clone --depth 1 https://github.com/tatuke/agent-switchWrote 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/tatuke/agent-switch/agents-md)<a href="https://agentmods.dev/instructions/tatuke/agent-switch/agents-md"><img src="https://agentmods.dev/badge/instructions/tatuke/agent-switch/agents-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/tatuke/agent-switch/agents-md"><img src="https://agentmods.dev/badge/instructions/tatuke/agent-switch/agents-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 | $0.00552 | $0.00552 |
| Opus 5.5 | $0.00221 | $0.00221 |
| Sonnet 5.5 | $0.00110 | $0.00110 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
agent-switch 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 1mo 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ASTP Project Rules
Cross-agent project rules for this repository. EVERY AI agent working here (Claude Code, opencode, codex, openclaw, ...) MUST follow this file.
Platform-specific notes live in the corresponding agent file (e.g., CLAUDE.md) and MUST reference — never duplicate — the rules below. Claude Code reads AGENTS.md natively, so AGENTS.md is the single canonical source.
Security Red Line (HIGHEST PRIORITY)
- NEVER put real infrastructure info in any file that could be committed to git. This includes:
- Real internal IPs (10.x.x.x, 192.168.x.x, 172.16-31.x.x)
- Real usernames
- Real hostnames, real email addresses, real ports, real internal paths
- ALWAYS use generic example values:
user@source-host,[email protected],/path/to/bundle - Applies to ALL files: README, INTRODUCE.md, config examples, test fixtures, comments, documentation
- Self-check BEFORE every file write. Violation = critical error. No exceptions.
- NEVER commit real secrets, API keys, tokens, or private keys. Use references or placeholder values.
Language
- Documentation is English-first:
README.md,packys_en.md,adaptys_en.mdare the canonical specs. README.zh.mdis the Simplified Chinese mirror — update it in the same commit when the English README changes.- Code, identifiers, comments, commit messages: English.
Build & Test
- Node.js >= 20, TypeScript. Commands:
npm run build/test/typecheck/lint. - Run
npm run typecheckandnpm run testbefore every commit. Do not commit with failing checks. - Tests use vitest; fixtures must follow the Security Red Line (generic values only).
Protocol Docs
packys_en.md(packing spec) andadaptys_en.md(adapting spec) define the bundle format.- Any change to the bundle structure MUST update both specs in the same commit so the two sides stay consistent.
- The bundle manifest version (
manifest.yaml→bundle_version) must be bumped on any structural change.
Git Conventions
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.
- 1mo ago First seen · 41 lines · 552 tokens per session scan A 256122a14231
agent-switch AGENTS.md is an instructions file published in the GitHub repository tatuke/agent-switch (2 stars, last pushed 14d ago), licensed MIT. It adds 552 tokens to every session, about $0.0022 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 2026-09-24.
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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.