Borrowing it
Nothing to install: this file belongs to grapeot/tavily-skill. 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/grapeot/tavily-skill/master/AGENTS.mdgit clone --depth 1 https://github.com/grapeot/tavily-skillWrote 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/grapeot/tavily-skill/agents-md)<a href="https://agentmods.dev/instructions/grapeot/tavily-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/grapeot/tavily-skill/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/grapeot/tavily-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/grapeot/tavily-skill/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 | $0.00350 | $0.00350 |
| Opus 5.5 | $0.00140 | $0.00140 |
| Sonnet 5.5 | $0.00070 | $0.00070 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
tavily-skill 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.
What it actually says
AGENTS.md — Tavily Skill
Layout
src/tavily_skill/— Python package (cli.pyowns argparse + Tavily calls).tests/— pytest suite (offline-first).docs/— PRD, RFC, testing notes, working log.skills/— AI-agent skill entrypoint (skill_tavily.md, English).scripts/run_cli.sh— convenience runner once.venvexists.
Treat repository root as the default cwd in docs and examples; avoid machine-specific absolute paths.
Expectations
- After substantive edits, append a dated bullet under
docs/working.md→ Changelog and capture pitfalls under Lessons Learned. - Prefer small, focused commits.
- Language for documentation inside this repo stays English.
- Never commit vault-specific
op://defaults or raw API keys — operators configure env vars locally.
Environment
Python 3.10+. Use uv pip install -e '.[dev]' inside ./.venv. Integration tests spend Tavily credits; gate them with RUN_TAVILY_INTEGRATION=1.
Latency benchmark against the real API (opt-in, spends credits): RUN_TAVILY_LATENCY=1 .venv/bin/python benchmarks/latency.py --queries 4 --repeats 3. Without the env var it prints a skip note and exits 0; see benchmarks/README.md.
Packaging
- Python package:
tavily_skill - Optional console entry point from
pyproject.toml:tavily-skill
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 Changed · +2 lines · +65 tokens per session 6144046c160a
- 2mo ago First seen · 28 lines · 285 tokens per session scan A 5cdeb4fc0d02
tavily-skill AGENTS.md is an instructions file published in the GitHub repository grapeot/tavily-skill (13 stars, last pushed 26d ago), licensed MIT. It adds 350 tokens to every session, about $0.0014 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 2026-08-30.
tavily-skill AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tavily-skill AGENTS.mdgrapeot/tavily-skill | Instructions file | 13 | 26d ago | MIT | A | 350 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |