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/nxtsoft/cgraph/claude-mdgit clone --depth 1 https://github.com/Nxtsoft/CGraphWhat 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 | $0.02217 | $0.02217 |
| Opus 5 | $0.01108 | $0.01108 |
| Sonnet 5 | $0.00443 | $0.00443 |
| Haiku 4.5 | $0.00222 | $0.00222 |
Grade A, and why
CGraph CLAUDE.md scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`igraph`, `curl`, `nlohmann-json`, `utf8proc`; tree-sitter is vendored under `vendor/tree-sitter`. How it starts
The opening of the file, as written. The whole thing — 136 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
cgraph is a native C++20/C graph-analysis engine that ports Graphify's deterministic
code-graph pipeline. It produces a Graphify-compatible graph.json (node-link format) plus
HTML/SVG/Obsidian/Cypher exports, and serves low-latency graph queries from a resident
per-project daemon. The design split is deliberate: the native binary owns deterministic
graph work, chunk planning, fragment validation, and local graph mutation. Hosts own all
model/LLM logic — there are no API keys, providers, or LLM clients in the binary. Semantic
enrichment enters only as host-written, validated fragment files. See
docs/host-skill-contract.md.
Build, test, run
The project uses CMake presets + vcpkg. vcpkg is vendored at ./.vcpkg and the presets
read $env{VCPKG_ROOT}, which is not set in the environment — you must export it:
export VCPKG_ROOT="$PWD/.vcpkg" # required; presets fail without it
cmake --preset default # configure -> build/default (Ninja, Debug)
cmake --build build/default # build all targets
ctest --preset default # run the smoke tests (output-on-failure)
ctest --preset default -R cgraph_detect_test # run a single test by name (regex)
Other presets: sanitizers (ASan/UBSan, build/sanitizers) and fuzzers (libFuzzer +
ASan/UBSan, build/fuzzers, requires CGRAPH_BUILD_FUZZERS=ON). System deps via vcpkg:
igraph, curl, nlohmann-json, utf8proc; tree-sitter is vendored under vendor/tree-sitter.
Built binaries land in build/default/src/<target>/:
cgraph(cli) — one-shot:cgraph --root PATH --out cgraph-outbuilds the graph and writes all exports.graphd(daemon) — resident per-project server; also--benchmark-query --graph PATH --query TEXT.cgraph-client(client) — thin client:cgraph-client --root PATH <query|path|explain|update|status|shutdown> [JSON params].cgraph-mcp(mcp) — MCP server (stdio JSON-RPC) fronting the daemon ops.
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 · 136 lines · 2,217 tokens per session scan A 06f4e16cee46
CGraph CLAUDE.md is an instructions file published in the GitHub repository Nxtsoft/CGraph (2 stars, last pushed 5d ago), licensed MIT. It adds 2,217 tokens to every session, about $0.0111 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain 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.