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/ofabiodev/stfu/agents-mdgit clone --depth 1 https://github.com/ofabiodev/stfuWhat 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 | $0.00149 | $0.00149 |
| Opus 5 | $0.00075 | $0.00075 |
| Sonnet 5 | $0.00030 | $0.00030 |
| Haiku 4.5 | $0.00015 | $0.00015 |
Grade A, and why
stfu 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.
What it actually says
STFU
Keep responses direct, concise, and focused on the requested result.
- Start with the answer.
- No greeting, preamble, recap, filler, praise, or generic closing.
- Do not explain unless the user asks or correctness requires it.
- Prefer the shortest useful response; use bullets only when they reduce length.
- Preserve correctness, safety, accessibility, and necessary detail.
- If the user asks for more detail, expand normally.
Codex and Claude Code inject the full rules from skills/stfu/SKILL.md through the bundled plugin hooks. Cursor uses the bundled always-applied rule. Standalone skill usage keeps /stfu on and /stfu off when the host supports those commands.
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 · 13 lines · 149 tokens per session scan A a29bb64e6702
stfu AGENTS.md is an instructions file published in the GitHub repository ofabiodev/stfu (3 stars, last pushed 8d ago), licensed MIT. It adds 149 tokens to every session, about $0.0007 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
nanobrowser CLAUDE.md
Instructions for nanobrowser/nanobrowser, covering claude.md, project overview, development commands, workspace tips and architecture.
octocode AGENTS.md
AGENTS.md instructions for bgauryy/octocode, covering agents.md — octocode monorepo, dogfood, architecture, packages and tools.
thinkrail AGENTS.md
Instructions for JetBrains/thinkrail, covering thinkrail, module structure & boundaries (top-priority requirement), engine: pi only, in-process, architecture (three rings) and repo layout.
bifrost AGENTS.md
Instructions for bifrost-proxy/bifrost, covering bifrost 项目开发规则, 执行心法, 执行模式与完成定义, 任务模式判定 and 变更类型与验证路由（先判定，后执行）.
octocode CLAUDE.md
Claude Code instructions for bgauryy/octocode: Read AGENTS.md. Discover repository skills under .agents/skills and activate only those matching the task.
Commonly-used-high-value-skills AGENTS.md
Instructions for seaworld008/Commonly-used-high-value-skills, covering repository agent instructions, architecture overview, installation root by client, golden rules and automated operations (sop for ai agents).