hermit-agent CLAUDE.md

hermit-agent CLAUDE.md is an instructions file for coding agents from cafitac/hermit-agent. It costs 193 tokens per session, scanned A, original, MIT.

Project instructions for Hermit, a small MCP coding executor for Claude Code and Codex. MCP is a standard way for an AI assistant to call tools, while Hermit provides task execution, model routing, repository operations, and command-line setup.

In plain words
What is it for?
Use it when developing or testing Hermit, installing its Claude or Codex integration, running its MCP server, checking its health, or working on its Python codebase.
Why use it?
It gives contributors a clear map of the project's modules, public commands, tests, and product boundary. This helps prevent changes that turn it into a different kind of product.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/cafitac/hermit-agent/claude-md
Clone the repo
git clone --depth 1 https://github.com/cafitac/hermit-agent

Wrote 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.

agentmods badge for hermit-agent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cafitac/hermit-agent/claude-md.svg)](https://agentmods.dev/instructions/cafitac/hermit-agent/claude-md)
Your own site
<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>
Per session 193 This file is loaded in full into every session.
When invoked 193 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash 828fe508d29d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

CLAUDE.md · 33 lines

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 tools
  • hermit_agent/gateway/ — background task lifecycle and model routing
  • hermit_agent/loop.py — LLM/tool execution loop
  • hermit_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.

Changes

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.

  1. 3d ago First seen · 33 lines · 193 tokens per session scan A 828fe508d29d

Subscribe to this mod's changes

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.

Related

Other instructions, from other repositories