Borrowing it
Nothing to install: this file belongs to PrithviSeran/hunch-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/PrithviSeran/hunch-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/PrithviSeran/hunch-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/prithviseran/hunch-mcp/claude-md)<a href="https://agentmods.dev/instructions/prithviseran/hunch-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/prithviseran/hunch-mcp/claude-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/prithviseran/hunch-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/prithviseran/hunch-mcp/claude-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 | $0.00408 | $0.00408 |
| Opus 5.5 | $0.00163 | $0.00163 |
| Sonnet 5.5 | $0.00082 | $0.00082 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
hunch-mcp CLAUDE.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
CLAUDE.md
See AGENTS.md for how this codebase works and the gotchas that matter
(the focus-free contract, AX-layer traps, the NSWorkspace frontmost trap, adding tools,
the vision path, plus packaging/release). It's the canonical guide for coding agents; this file just points to it so
Claude Code loads it.
Quick reminders:
- One feature/bug/patch per branch; commits stay atomic. See AGENTS.md → Branches and commits.
- Run tests:
.venv/bin/python -m pytest tests/ - Adding/removing a tool changes the count in
tests/test_smoke.py::test_tool_count(now 29). - Never read the frontmost app with
NSWorkspace.frontmostApplication()— use_frontmost(). - Keep Hunch focus-free: shared-input fallbacks must
activate()-or-refuse and bumpMacSession.disturbances. - The AX tree walk is serial by design — batching (
get_attrs) is the IPC win; reading across threads doesn't help (the target app answers AX on one main thread). Don't re-add a concurrent prefetch (removed in 0.5.1). See AGENTS.md → AX-layer knowledge. - Releasing? The sdist is allowlisted (
[tool.hatch.build.targets.sdist]) so it does not sweep the git-excludedbench/(that once made a 368 MB sdist). PyPI package ishunch-sdk; on each release also bumpserver.json's version and the separatehomebrew-hunchformula. See AGENTS.md → Packaging. - The model-facing contract is
playbook.py(HUNCH_PLAYBOOK), served as the MCP server'sinstructions. To change agent behavior, edit it there, not the tool docstrings.
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 · +1 lines · +24 tokens per session 44369c12fa78
- 2mo ago First seen · 23 lines · 384 tokens per session scan A 6c133ae8c142
hunch-mcp CLAUDE.md is an instructions file published in the GitHub repository PrithviSeran/hunch-mcp (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 408 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 2026-08-30.
hunch-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hunch-mcp CLAUDE.mdPrithviSeran/hunch-mcp | Instructions file | 23 | 2d ago | Apache-2.0 | A | 408 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | 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 |