grafel CLAUDE.md

grafel CLAUDE.md is an instructions file for Claude Code from cajasmota/grafel. It costs 735 tokens per session, scanned A, original, MIT.

Repository instructions for using Grafel MCP, a tool that maps relationships in source code, alongside grep, which searches raw text. They explain when each approach is suitable.

In plain words
What is it for?
Use them to navigate call graphs, locate code entities, reduce a search area, and then verify exact source patterns with grep.
Why use it?
They help you answer structural questions, such as which services call a function, without relying on incomplete text searches. They also clarify when grep is better for finding every matching line or statement.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions AGENTS.md.

Install

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.

agentmods
npx agentmods add instructions/cajasmota/grafel/claude-md
Clone the repo
git clone --depth 1 https://github.com/cajasmota/grafel

Made for: Claude Code.

Wrote 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.

agentmods badge for grafel CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cajasmota/grafel/claude-md.svg)](https://agentmods.dev/instructions/cajasmota/grafel/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cajasmota/grafel/claude-md"><img src="https://agentmods.dev/badge/instructions/cajasmota/grafel/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 735 This file is loaded in full into every session.
When invoked 735 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00735 $0.00735
Opus 5 $0.00367 $0.00367
Sonnet 5 $0.00147 $0.00147
Haiku 4.5 $0.00073 $0.00073

Measured 6d ago against content hash 60da535f3493, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

grafel 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 6d 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.

CLAUDE.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to use grafel MCP vs grep

grafel MCP gives you a navigable, accurate map of the code; grep gives you raw pattern matches. Use MCP for structural questions: who calls X? what is the flow? where does Y live in the graph? Use grep for raw enumeration: every if err != nil, every import line, every TODO. Pair them: MCP narrows the search space; grep verifies edge-property questions MCP can't answer yet.

Three concrete examples

MCP-good — structural navigation: "Which services call OrderService.CreateOrder?" → grafel_find + grafel_find_callers gives you the precise call graph with repo context, in one round-trip. grep would require you to know every caller file location across every repo in the group.

grep-good — raw enumeration: "List every if err != nil block that is missing a log.Error call." → grep is the right tool. grafel models control flow at the entity level, not at the statement level. Raw text search on the source files is faster and more complete for this class of pattern.

Paired — search space reduction then raw verify: "Does any service leak the internal User.PasswordHash field in an HTTP response?" →

  1. MCP: grafel_find entity_type=http_endpoint_definition + grafel_find_paths to identify every endpoint that touches User. Narrows a 500-file repo to 8 handlers.
  2. grep: search only those 8 handler files for PasswordHash to confirm whether it appears in any serialisation path.

For grafel developer workflow, architecture decisions, and contributing guidelines see docs/adrs/ and AGENTS.md.

grafel MCP

This repo is part of grafel group grafel. grafel is an architecture knowledge graph available via MCP. When you (an AI coding agent) need to understand how this codebase fits together, prefer the grafel MCP tools over grep + reading files.

When to use grafel instead of grep

Question shape Prefer
"Where is X defined?" grafel_find
"What does X look like + its neighbors?" grafel_inspect
"Who calls X?" grafel_expand / grafel_find_callers
"End-to-end flow when user does X?" grafel_traces
"How does the frontend talk to the backend?" grafel_cross_links
"Show me the source of X" grafel_get_source

Read the full file on GitHub · 64 lines

Changes

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.

  1. 6d ago First seen · 64 lines · 735 tokens per session scan A 60da535f3493

Subscribe to this mod's changes

grafel CLAUDE.md is an instructions file published in the GitHub repository cajasmota/grafel (12 stars, last pushed yesterday), licensed MIT. It adds 735 tokens to every session, about $0.0037 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.

Related

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).

microsoft/vscode · 6,785 tokens

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

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.

github/spec-kit · 7,104 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens