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/magic5644/graph-it-live/claude-mdgit clone --depth 1 https://github.com/magic5644/Graph-It-LiveWrote 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/magic5644/graph-it-live/claude-md)<a href="https://agentmods.dev/instructions/magic5644/graph-it-live/claude-md"><img src="https://agentmods.dev/badge/instructions/magic5644/graph-it-live/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 | $0.01643 | $0.01643 |
| Opus 5 | $0.00822 | $0.00822 |
| Sonnet 5 | $0.00329 | $0.00329 |
| Haiku 4.5 | $0.00164 | $0.00164 |
Grade A, and why
Graph-It-Live 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
# Build
npm run build # Bundle extension via esbuild + copy WASM files to dist/wasm/
npm run build:cli # Build CLI only
npm run watch # Rebuild on change
# Test
npm test # All tests (Vitest)
npm run test:unit # Unit tests only
npm run test:cli # CLI tests
npm run test:coverage # Coverage report (V8)
npm run test:watch # Watch mode
npx vitest run tests/path/to/foo.test.ts # Single test file
# E2E (real VS Code Electron instance)
npm run test:vscode # E2E from source
npm run test:vscode:vsix # E2E from packaged .vsix
# Lint / Types
npm run lint # ESLint check
npm run lint:fix # ESLint auto-fix
npm run check:types # TypeScript strict check
# Package
npm run package # Build .vsix
npm run package:verify # Verify no .map files in package
# dependencies
npm audit
npm audit fix
cve-lite --verbose # use npm install -g cve-lite to install cve-lite
Requires Node.js ≥22. No native compilation needed — Tree-sitter uses WASM.
Architecture
VS Code extension + standalone CLI + MCP server for AI-friendly dependency visualization.
Four-Layer Structure
-
analyzer/— Pure Node.js. NO vscode imports. Core analysis: Spider (file-level regex import parsing), SymbolAnalyzer (ts-morph AST), LspCallHierarchyAnalyzer (VS Code LSP), PathResolver, caching.analyzer/callgraph/— Live Call Graph: GraphExtractor (Tree-sitter queries), CallGraphIndexer (sql.js SQLite), CallGraphQuery (BFS), cycleUtils.
-
extension/— VS Code host. GraphProvider orchestrates 8+ services inextension/services/: BackgroundIndexingManager, CallGraphViewService, CommandRegistrationService, EditorEventsService, GraphViewService, SymbolViewService, WebviewMessageRouter, etc. -
mcp/— MCP server (stdio transport). NO vscode imports. 23 tools (McpToolNameinsrc/mcp/types.ts) for LLM clients (Copilot, Claude, Cursor). Standalone Node.js process. Includesreview_pr— deterministic local Git-diff review (also exposed via CLI asgraph-it review-prand as a reusable GitHub Action.github/actions/graph-it-review-gate).
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.
- 4d ago First seen · 122 lines · 1,643 tokens per session scan A 5a8a25fb3355
Graph-It-Live CLAUDE.md is an instructions file published in the GitHub repository magic5644/Graph-It-Live (43 stars, last pushed 6d ago), licensed MIT. It adds 1,643 tokens to every session, about $0.0082 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.
Other instructions, from other repositories
agy-plugin-cc CLAUDE.md
Instructions for Vit129/agy-plugin-cc, covering agy-plugin-cc — claude code guide, agent memory, global-first rule, project context (auto-loaded every session) and project summary.
antigravity-testing-kit GEMINI.md
Instructions for anhtester/antigravity-testing-kit, covering gemini ai - global automation agent rules, git pull restriction rule, browser rules (mandatory), 🖥️ viewport & mode and 🔄 thứ tự debug bắt buộc (playwright mcp).
SkillEngine CLAUDE.md
Claude Code instructions for borhen68/SkillEngine, covering skillengine, project structure, skills by phase, conventions and commands.
ag-sdd AGENTS.md
AGENTS.md instructions for stormlive-ai/ag-sdd, covering agents.md — anti-gravity spec-driven development (ag-sdd), 1. purpose & philosophy, 2. sdd workflow lifecycle, phase 1 — discovery (mandatory clarification gate) and phase 2 — spec generation.
addyosmani-agent-skills-zh CLAUDE.md
Claude Code instructions for vinvcn/addyosmani-agent-skills-zh, covering agent-skills, 项目结构, 按阶段划分的 skills, 约定 and 命令.
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).