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/phoenixrr2113/codebase-graph/claude-mdgit clone --depth 1 https://github.com/Phoenixrr2113/codebase-graphWhat 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 | $0.03376 | $0.03376 |
| Opus 5 | $0.01688 | $0.01688 |
| Sonnet 5 | $0.00675 | $0.00675 |
| Haiku 4.5 | $0.00338 | $0.00338 |
Grade A, and why
codebase-graph 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.
How it starts
The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeGraph: AI Assistant Skill Document
CodeGraph indexes codebases into a graph database (FalkorDB) and provides MCP tools for code search, context retrieval, repository analysis, knowledge management, and raw graph queries.
Quick Start
Check if a codebase is indexed:
codebase({ action: "status" })
On a fresh install this returns configured: false and setupRequired: true. An empty database is valid and ready for setup.
If no projects are configured, save an absolute project path and then index it:
codebase({ action: "configure", projectAction: "set", projects: ["/path/to/project"] })
codebase({ action: "reindex", mode: "full", scope: "/path/to/project" })
Configuration does not index the project. Reindexing parses structure first and finishes embeddings. With no provider or provider key set, local nomic-ai/nomic-embed-text-v1.5 embeddings are the default. The first use downloads approximately 132 MiB and reports progress.
Tool Reference (5 tool groups, 25 actions)
1. search: Find code and knowledge
Vector search with optional cross-encoder reranking when a supported provider key is configured. Without one, search keeps vector-search ordering. Local 768-dimension embeddings remain the no-key default. Results include complexity, callers, callees, importerCount, and linkedKnowledge.
| Action | Use When | Required Params |
|---|---|---|
find |
Looking for files, functions, classes, symbols | query |
context |
Need relationships and structure for a file or symbol | file or symbol |
Search modes: searchScope: 'code' (default), 'knowledge', 'all' (RRF fusion).
Examples:
search({ action: "find", query: "parseProject" })
search({ action: "find", query: "authentication", searchScope: "all" })
search({ action: "context", file: "src/service.ts", includeRelationships: true })
search({ action: "context", symbol: "enrichedSearchV2" })
Multi-step questions: for complex queries that need iterative refinement, chain search calls in your agent. Examine results, refine the query, and search again. CodeGraph stays focused on per-call retrieval quality; orchestration is the agent's job.
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 · 205 lines · 3,376 tokens per session scan A a75f37c49c11
codebase-graph CLAUDE.md is an instructions file published in the GitHub repository Phoenixrr2113/codebase-graph (7 stars, last pushed 8d ago), licensed MIT. It adds 3,376 tokens to every session, about $0.0169 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.
Other instructions, from other repositories
arbor CLAUDE.md
Claude Code instructions for getArbor-dev/arbor, covering claude.md, commands, build, test all crates and test single crate.
arbor copilot-instructions.md
Copilot instructions for getArbor-dev/arbor: Ensure that the previous step has been marked as completed. Call project setup tool with projectType parameter. Run scaffolding command to create project files and folders. Use '.' as the working directory. If no appropriate projectType is available, search documentation…
mcp-codebase AGENTS.md
AGENTS.md instructions for DmitriyOT/mcp-codebase, covering agents.md, documentation workflow (required), project overview, tech stack and requirements and build and run commands.
codeweave-mcp CLAUDE.md
Instructions for semihkayan/codeweave-mcp, covering claude.md, what this project is, build & run, architecture and layers.
ai-workflow AGENTS.md
Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.
trackly-cli CLAUDE.md
Claude Code instructions for trackly-app/trackly-cli, covering trackly-cli, tech stack, backend production source of truth, directory structure and key commands.