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/techcraze00/codegraphx/claude-mdgit clone --depth 1 https://github.com/techcraze00/CodeGraphXWhat 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 | $0.01874 | $0.01874 |
| Opus 5 | $0.00937 | $0.00937 |
| Sonnet 5 | $0.00375 | $0.00375 |
| Haiku 4.5 | $0.00187 | $0.00187 |
Grade B, and why
CodeGraphX CLAUDE.md scanned grade B with 1 finding 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 yesterday.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| `src/setup/adapters/*.js` | Per-CLI adapters (claude, gemini, antigravity, opencode, cursor): `configureMcp()` (native `<cli> mcp add` → JSON file fallback) + `installSkill()`. MCP cmd = absolute node + bundled `bin/cg How it starts
The opening of the file, as written. The whole thing — 120 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
# One-command setup: wire CodeGraphX (MCP server + skill) into your coding CLIs
node bin/cgx setup # interactive multi-select of detected CLIs
node bin/cgx setup --agents claude,gemini --yes # non-interactive
node bin/cgx setup --project # project scope instead of user/global
# Run all tests
npm test
# Run a single test file
npx jest tests/server/mcp-server.test.js --verbose
# Run tests matching a pattern
npx jest --testNamePattern="should trace impact"
# Scan the local codebase (generates .codegraphx/ artifacts and .codegraphx.db)
node bin/cgx init
# Start the MCP server (stdio transport, used by AI agents)
node bin/cgx-mcp
# Query a symbol
node bin/cgx query <symbolName>
# Trace impact
node bin/cgx impact <symbolName> --direction downstream --depth 5
# Run diagnostics
node bin/cgx doctor --json
Architecture Overview
CodeGraphX is a codebase graph engine for AI agents. It parses source files with Tree-sitter, stores an append-only semantic graph in SQLite (or Postgres), and exposes it via a CLI and an MCP server.
Core data flow
Source files
→ parser.js (Tree-sitter per-language adapters)
→ entities.js (SymbolEntity, FileEntity, EdgeEntity)
→ scanner.js (orchestrates full scan, writes DB + file artifacts)
→ store/sql-store.js (Kysely ORM — append-only temporal DB)
After a scan, the SQLite file (.codegraphx.db in the project root) is the source of truth. The .codegraphx/ directory holds derived artifacts: codegraph.html, codegraph-graph.json, codegraph.toon, file_index.toon, symbols.bloom, and cache.json.
Temporal / bi-temporal storage
The DB schema is intentionally append-only. Rows are never deleted. Instead, every files, symbols, and edges row carries valid_from_commit_id and valid_to_commit_id. NULL in valid_to_commit_id means the row is currently active. This pattern is implemented throughout sql-store.js and the migration in src/db/migrations/001_initial_schema.js.
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.
- yesterday First seen · 120 lines · 1,874 tokens per session scan B 7638e1b9123f
CodeGraphX CLAUDE.md is an instructions file published in the GitHub repository techcraze00/CodeGraphX (3 stars, last pushed 12d ago), licensed MIT. It adds 1,874 tokens to every session, about $0.0094 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
AionUi AGENTS.md
Instructions for iOfficeAI/AionUi, covering aionui - project guide, code conventions, file & directory structure, naming and ui library & icons.
spec-kitty AGENTS.md
Instructions for Priivacy-ai/spec-kitty, covering spec kitty development guidelines, ⚠️ critical: load the project charter first, ⚠️ critical: template source location, ⚠️ critical: use canonical sources, never improvise and ⚠️ critical: git workflow — no direct pushes to origin/main.
coral CLAUDE.md
Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).
gemini-cli-desktop AGENTS.md
Instructions for Piebald-AI/gemini-cli-desktop, a project described as: Web/desktop UI for Gemini CLI/Qwen Code. Manage projects, switch between tools, search across past conversations, and manage MCP servers, all from one multilingual interface, locally or remotely.
sessionview AGENTS.md
Instructions for tyql688/sessionview, covering sessionview, commands, app / frontend, gates must pass under both feature sets: default (gui) and and --no-default-features --features headless.
SubFrame AGENTS.md
Instructions for Codename-11/SubFrame, covering subframe - subframe project, core working principle, relationship to native ai tools, session start and concurrent work & worktrees.