Borrowing it
Nothing to install: this file belongs to James-Chahwan/repo-graph. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/James-Chahwan/repo-graph/main/CLAUDE.mdgit clone --depth 1 https://github.com/James-Chahwan/repo-graphWrote 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/james-chahwan/repo-graph/claude-md)<a href="https://agentmods.dev/instructions/james-chahwan/repo-graph/claude-md"><img src="https://agentmods.dev/badge/instructions/james-chahwan/repo-graph/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.
<a href="https://agentmods.dev/instructions/james-chahwan/repo-graph/claude-md"><img src="https://agentmods.dev/badge/instructions/james-chahwan/repo-graph/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.04402 | $0.04402 |
| Opus 5.5 | $0.01761 | $0.01761 |
| Sonnet 5.5 | $0.00880 | $0.00880 |
| Haiku 4.5 | $0.00440 | $0.00440 |
Grade E, and why
repo-graph CLAUDE.md scanned grade E with 3 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 22d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
# curl -s https://pypi.org/pypi/glia-py/json | python -c "import sys,json;[print(f['filename']) for f in json.load(sys.stdin)['urls']]" Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf dist/ && python -m build Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# curl -s https://pypi.org/pypi/glia-py/json | python -c "import sys,json;[print(f['filename']) for f in json.load(sys.stdin)['urls']]" How it starts
The opening of the file, as written. The whole thing — 203 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.
What This Is
A thin Python MCP server that wraps the glia Rust engine (crate glia-py, PyPI glia-py). It exposes 6 MCP tools — orient, find, impact, trace, read, refresh — over any codebase. Each is a natural verb backed by an engine primitive (v0.5.0: find, blast_radius, cross_stack_trace, resolve, entry_flows, coverage, governing_docs), so the wrapper stays thin — the engine owns lookup, traversal, ranking, file/line locating, and the live (dead-code) flag.
The Python side is ~900 lines across 4 files. All parsing, graph building, storage (.gmap), activation, ranking, locating, and liveness happen in Rust. The Python package only hosts the MCP server, the CLI entrypoints, and a thin wrapper over the pyo3 bindings.
Commands
# Install (editable, for development)
pip install -e .
# Run the MCP server (points at a target repo)
repo-graph --repo /path/to/target-repo
# Initialise a new target repo (writes .mcp.json + CLAUDE.md instructions + first graph)
repo-graph-init --repo /path/to/target-repo
Python 3.11+ required. Runtime deps: mcp[cli]>=2,<3 (2.x renamed FastMCP → MCPServer; ported in 0.5.1), glia-py==0.5.1 (glia pins consumers exactly per release), watchdog>=3.0,<7.
Cache reuse on cold start
The wrapper caches the graph at <repo>/.glia/graph/ (sharded .gmap files). Since glia 0.5.0 (LC.8) load_from_gmap(dir, repo_path) self-heals — it rebuilds a stale, old-format or missing layout itself and writes it back — so get_graph() has no is_stale pre-check any more:
load_from_gmap(default_gmap_dir(repo), repo)— serves the layout, rebuilding it in place if it can't.ValueError→ fall back to_build_graph()(a fullgenerate+save_to_default).
generate is a pure build in 0.5.0: it writes no layout, so the explicit save_to_default in _build_graph is the only thing keeping the next cold start fast. Cache writes are best-effort: a read-only filesystem or perms error doesn't break the live graph.
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.
- 22d ago Changed · +10 lines · +455 tokens per session 2ee44a247a22
- 1mo ago Changed · +17 lines · +706 tokens per session 986a810095c9
- 1mo ago Changed · +2 lines · +76 tokens per session 5f91cd4d29a3
- 1mo ago First seen · 174 lines · 3,165 tokens per session scan E d40fcd599460
repo-graph CLAUDE.md is an instructions file published in the GitHub repository James-Chahwan/repo-graph (87 stars, last pushed 23d ago), licensed MIT. It adds 4,402 tokens to every session, about $0.0176 per session on Opus 5.5. A static security scan graded it E with 3 findings (downloads and executes remote code, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.