graph-of-skills: Instructions file for Claude Code

CLAUDE.md

graph-of-skills CLAUDE.md is an instructions file for Claude Code from davidliuk/graph-of-skills. It costs 1,901 tokens per session, scanned A, original, MIT.

Integration instructions for Graph of Skills, a system that stores skills in a searchable graph and exposes them to Claude Code through an MCP server. MCP is a way for an AI assistant to call an external tool during a conversation.

In plain words
What is it for?
Setting up the skill graph, discovering and retrieving skills from Claude Code, registering the server manually when automatic setup fails, and checking that the connection works.
Why use it?
They explain how to install the project, provide an embedding-service key, load a skill workspace, and make the skill search available automatically.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is davidliuk/graph-of-skills's own configuration. It tells Claude Code how to work on graph-of-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything graph-of-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to davidliuk/graph-of-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/davidliuk/graph-of-skills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/davidliuk/graph-of-skills

Made for: Claude Code.

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 graph-of-skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/davidliuk/graph-of-skills/claude-md/github.svg)](https://agentmods.dev/instructions/davidliuk/graph-of-skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/davidliuk/graph-of-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/davidliuk/graph-of-skills/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.

agentmods 80×15 button for graph-of-skills CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/davidliuk/graph-of-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/davidliuk/graph-of-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,901 This file is loaded in full into every session.
When invoked 1,901 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01901 $0.01901
Opus 5 $0.00950 $0.00950
Sonnet 5 $0.00380 $0.00380
Haiku 4.5 $0.00190 $0.00190

Measured 6d ago against content hash 941288515cb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

graph-of-skills 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 6d 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 · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Graph of Skills — Claude Code Integration

GoS ships with a built-in MCP server that gives Claude Code direct access to the skill graph — search, retrieve, explore, and manage skills without leaving the conversation.

Setup

Prerequisites

  1. Install dependencies:

    uv sync
    
  2. Configure API keys — copy .env.example to .env and fill in your embedding provider (OpenAI, Gemini, or Azure):

    cp .env.example .env
    # Edit .env: set OPENAI_API_KEY or GEMINI_API_KEY
    
  3. Get a workspace — build from source for the current typed-directed constructor. Downloaded *_v1 workspaces are legacy reproduction artifacts and are rejected because their undirected edges cannot be repaired safely:

    # Option A: Download prebuilt workspaces
    ./scripts/download_data.sh --workspace
    
    # Option B: Build locally (needs embedding API)
    ./scripts/download_data.sh --skillsets
    uv run gos index data/skillsets/skills_200 \
      --workspace data/gos_workspace/skills_200_v1 --clear
    

Auto-Discovery (Recommended)

The .mcp.json at the project root auto-registers the MCP server. Open the project directory in Claude Code — the graph-of-skills server is immediately available, no extra steps.

Verify with:

claude mcp list

You should see graph-of-skills in the output.

Manual Registration

If auto-discovery doesn't work (e.g. you're working from a different directory), register manually:

# Basic registration
claude mcp add graph-of-skills -- uv run --directory /path/to/graph-of-skills gos-claude

# With an explicit workspace
claude mcp add graph-of-skills -- uv run --directory /path/to/graph-of-skills gos-claude \
  --workspace /path/to/graph-of-skills/data/gos_workspace/skills_200_v1

Switching Workspaces

The default workspace is set in .mcp.json. To use a different skill library size, edit the --workspace argument:

// .mcp.json
{
  "mcpServers": {
    "graph-of-skills": {
      "command": "uv",
      "args": ["run", "--directory", ".", "gos-claude",
               "--workspace", "data/gos_workspace/skills_2000_v1"]
    }
  }
}

Read the full file on GitHub · 195 lines

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. 6d ago Changed · +2 lines · +31 tokens per session 941288515cb9
  2. 12d ago First seen · 193 lines · 1,870 tokens per session scan A 5cb0f6d6c398

Subscribe to this mod's changes

graph-of-skills CLAUDE.md is an instructions file published in the GitHub repository davidliuk/graph-of-skills (206 stars, last pushed 12d ago), licensed MIT. It adds 1,901 tokens to every session, about $0.0095 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 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens