Borrowing it
Nothing to install: this file belongs to swang62/hatchet-mcp. 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/swang62/hatchet-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/swang62/hatchet-mcpWrote 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/swang62/hatchet-mcp/agents-md)<a href="https://agentmods.dev/instructions/swang62/hatchet-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/swang62/hatchet-mcp/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/swang62/hatchet-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/swang62/hatchet-mcp/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 | $0.00390 | $0.00390 |
| Opus 5.5 | $0.00156 | $0.00156 |
| Sonnet 5.5 | $0.00078 | $0.00078 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
hatchet-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 2mo 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
Project layout
src/
mcp/ -- MCP server (entry point for LLM clients)
hatchet_worker/ -- Hatchet worker + workflow implementations
langgraph/ -- LangGraph agent graph
shared/ -- Bridge layer between hatchet and langgraph
Gotchas
MCP universal 60s timeout:
Every MCP tool call times out after 60 seconds. The HITL interrupt resets the timer. If a tool call returns with needs_approval, the user must approve/reject via k8s_resume before the thread can continue. Do not poll or automate approvals on behalf of the user.
Hatchet cron is UTC-only:
No timezone parameter exists. The expression is hardcoded in scheduling.py:53. Changing the local time requires computing the equivalent UTC hour manually, and there is no DST handling.
Worker restart via serviceman (macOS launchd):
serviceman restart hatchet-worker after any code change to workflow or worker files. The worker script is at repo root (hatchet-worker.sh) — it runs uv run python src/hatchet_worker/worker.py. To register the worker as a login service:
serviceman add --name hatchet-worker -- ./hatchet-worker.sh
# check live logs
serviceman logs hatchet-worker
Two entrypoints, different purposes:
- MCP server:
uv run python src/mcp/k8s_server.py— for LLM clients - Hatchet worker:
uv run python src/hatchet_worker/worker.py— durable background agent
just lint = 3 tools:
ruff check src/ && ruff format src/ --check && basedpyright src/. Running only ruff check skips type-checking and format verification.
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.
- 2mo ago First seen · 33 lines · 390 tokens per session scan A a75e19107590
hatchet-mcp AGENTS.md is an instructions file published in the GitHub repository swang62/hatchet-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 390 tokens to every session, about $0.0016 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 2026-08-31.
hatchet-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hatchet-mcp AGENTS.mdswang62/hatchet-mcp | Instructions file | 1 | 2mo ago | MIT | A | 390 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | 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 | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |