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/gravitykit/mcp/claude-mdgit clone --depth 1 https://github.com/GravityKit/MCPWhat 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 | $0.00005 | $0.00005 |
| Opus 5 | $0.00003 | $0.00003 |
| Sonnet 5 | $0.00001 | $0.00001 |
| Haiku 4.5 | $0.00001 | $0.00001 |
Grade A, and why
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 2d 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.
This is a copy
100% identical to deepseek-harness CLAUDE.md — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
@AGENTS.md
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.
- 2d ago First seen · 2 lines · 5 tokens per session scan A 336cc4fbf19b
MCP CLAUDE.md is an instructions file published in the GitHub repository GravityKit/MCP (24 stars, last pushed 1mo ago), licensed MIT. It adds 5 tokens to every session, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to deepseek-harness CLAUDE.md, differing in 3 lines, and is treated as a copy.
Other instructions, from other repositories
woocommerce AGENTS.md
AGENTS.md instructions for woocommerce/woocommerce, covering woocommerce monorepo - ai agents documentation, project overview, navigation guide, which documentation to use? and available skills.
woocommerce CLAUDE.md
Claude Code instructions for woocommerce/woocommerce, a project described as: A customizable, open-source ecommerce platform built on WordPress. Build any commerce solution you can imagine.
mcp-wordpress CLAUDE.md
Instructions for docdyhr/mcp-wordpress: Project instructions live in AGENTS.md (DOX hierarchical framework — read it and its Child DOX Index before editing anything). This file exists only because Claude Code looks for CLAUDE.md specifically; keep it as a pointer, not a second copy, to avoid drift.
elementor-mcp CLAUDE.md
Claude Code instructions for msrbuilds/elementor-mcp, covering claude.md, project overview, companion projects (sibling folders, edit from here), dependencies & requirements and build & development commands.
wprig copilot-instructions.md
Copilot instructions for wprig/wprig, covering wp rig ai agents guide, 1. onboarding & state protocol, 2. architecture & build pipeline, 3. contract-first development and 4. configuration & content first.
wprig AGENTS.md
AGENTS.md instructions for wprig/wprig, covering wp rig ai agents guide, 1. onboarding & state protocol, 2. architecture & build pipeline, 3. contract-first development and 4. configuration & content first.