Borrowing it
Nothing to install: this file belongs to tech4242/mcphawk. 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/tech4242/mcphawk/main/AGENTS.mdgit clone --depth 1 https://github.com/tech4242/mcphawkWrote 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/tech4242/mcphawk/agents-md)<a href="https://agentmods.dev/instructions/tech4242/mcphawk/agents-md"><img src="https://agentmods.dev/badge/instructions/tech4242/mcphawk/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/tech4242/mcphawk/agents-md"><img src="https://agentmods.dev/badge/instructions/tech4242/mcphawk/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 | $0.01014 | $0.01014 |
| Opus 5.5 | $0.00406 | $0.00406 |
| Sonnet 5.5 | $0.00203 | $0.00203 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
mcphawk 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
MCPHawk is DevTools for MCP: it records real traffic between MCP clients and servers
(stdio wrapper, HTTP proxy, passive sniffer), stores it in SQLite, and serves a web UI plus
its own MCP server over the same data. Targets MCP spec 2026-07-28 and still supports the
older initialize handshake era.
Rules
- Use the local venv (
.venv/bin/python) and Makefile targets when they exist. - Add dependencies to
requirements.txt/requirements-dev.txtandpyproject.toml; neverpip installad hoc. - Before finishing:
make lintandmake test. Coverage must stay above 85% (make coveragefails below it). - New tests:
tests/unit/for isolated functions,tests/integration/<area>/for anything touching the DB, processes, network or HTTP. Build traffic withtests/traffic.py. - Follow the MCP spec and the official SDK instead of inventing custom protocol behaviour.
- Write PEP 8 from the start (ruff, line length 88, Python 3.10+).
Layout
capture/ -> store/recorder.py -> SQLite -> query.py + analysis/ -> web/app.py, mcp_server.py
protocol/: JSON-RPC framing, MCP semantics for both eras, secret masking, token estimatesstore/recorder.py: request/response pairing, multi round-trip chains, client/server identityquery.py: the one read layer; the web API and the MCP server must not query SQL themselvesruns.py: agent runs, computed at read time (client group, split at 5 min idle gaps).sessions.client_keystores only which client process a session belongs toinstall/: client config locations and install/uninstallotel/: OpenTelemetry export (semconv.pymaps to the MCP semantic conventions,exporter.pystreams OTLP frommcphawk up,prometheus.pyserves/metrics)frontend/: Vue 3 app, built intomcphawk/web/static(committed)
Commands
make install # deps + editable install + frontend deps
make test # or test-unit / test-integration / test-e2e ...
make dev # mcphawk up on :8484 + Vite on :5173
make build-frontend # then commit mcphawk/web/static; CI fails if it is stale
make demo # demo traffic from three SDK servers
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 · 72 lines · 1,014 tokens per session scan A e764fbcb7a43
mcphawk AGENTS.md is an instructions file published in the GitHub repository tech4242/mcphawk (16 stars, last pushed 1mo ago), licensed MIT. It adds 1,014 tokens to every session, about $0.0041 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.
mcphawk AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcphawk AGENTS.mdtech4242/mcphawk | Instructions file | 16 | 1mo ago | MIT | A | 1,014 | 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 |