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/cafitac/hermit-agent/claude-mdgit clone --depth 1 https://github.com/cafitac/hermit-agentWrote 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/cafitac/hermit-agent/claude-md)<a href="https://agentmods.dev/instructions/cafitac/hermit-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/cafitac/hermit-agent/claude-md.svg" alt="Measured on agentmods" 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 | $0.00193 | $0.00193 |
| Opus 5 | $0.00097 | $0.00097 |
| Sonnet 5 | $0.00039 | $0.00039 |
| Haiku 4.5 | $0.00019 | $0.00019 |
Grade A, and why
hermit-agent 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 3d 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
Hermit Project — MCP Executor
Hermit is a minimal MCP coding executor for Claude Code and Codex. Python 3.11+, FastAPI.
Key modules
hermit_agent/mcp_server.py— the four public MCP task toolshermit_agent/gateway/— background task lifecycle and model routinghermit_agent/loop.py— LLM/tool execution loophermit_agent/tools/— repository operations under the permission policy
Public CLI
hermit install claude
hermit install codex
hermit mcp-server
hermit doctor
Tests
.venv/bin/python -m pytest tests/
Product boundary
Hermit is an MCP executor, not a standalone chat UI. Do not add a terminal UI, host-specific interactive protocol, or unrelated orchestration product without an explicit product decision.
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.
- 3d ago First seen · 33 lines · 193 tokens per session scan A 828fe508d29d
hermit-agent CLAUDE.md is an instructions file published in the GitHub repository cafitac/hermit-agent (4 stars, last pushed 7d ago), licensed MIT. It adds 193 tokens to every session, about $0.0010 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
row-bot AGENTS.md
Instructions for siddsachar/row-bot, covering agents.md, project identity, ground rules, repository map and before editing.
row-bot CLAUDE.md
Instructions for siddsachar/row-bot, a project described as: Row-Bot - Personal AI Sovereignty. A local-first AI assistant with integrated tools, a personal knowledge graph, voice, vision, shell, browser automation, scheduled tasks, health tracking, and messaging channels. Run locally via Ollama or add opt-in cloud…
little-coder AGENTS.md
Instructions for itayinbarr/little-coder, covering little-coder, capabilities & autonomy, runtime invariants, available tools and file & shell.
cicero AGENTS.md
AGENTS.md instructions for 5uck1ess/cicero, covering agent guidance, product boundary, toolchain, verification and reliability and security invariants.
cicero CLAUDE.md
Claude Code instructions for 5uck1ess/cicero, a project described as: Self-hosted voice for coding agents. Talk from any browser or a Telegram call, interrupt mid-sentence, clone any voice, and hand real work to agents that ship PRs. Local STT/TTS; real-time voice client for ACP.
pxx AGENTS.md
Instructions for cdnwetzel/pxx, covering agents.md — working agreements for ai agents in this repo, what this is, commands, hard rules and conventions.