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/ranteck/graph-engineer/claude-mdgit clone --depth 1 https://github.com/Ranteck/graph-engineerWhat 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 | $0.01910 | $0.01910 |
| Opus 5 | $0.00955 | $0.00955 |
| Sonnet 5 | $0.00382 | $0.00382 |
| Haiku 4.5 | $0.00191 | $0.00191 |
Grade A, and why
graph-engineer 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.
This is a copy
86% identical to graph-engineer AGENTS.md — 32 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 131 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 repository is
This repo is a single Claude Code skill package named graph-engineer (plus its
README/LICENSE). There is no application code, no build step, no test suite, and no
package manifest — the repo's only artifact is the skill definition itself:
skills/graph-engineer/
├── SKILL.md # the skill's instructions (source of truth)
└── references/
├── goal-templates.md # ready-to-use /goal templates per scenario
├── quality-gate-detection.md # generic quality-gate command resolver algorithm
├── elevated-assurance.md # optional opt-in multi-lens CRITIQUE variant
├── backend-selection.md # opt-in per-cycle writer/reviewer routing
└── sources.md # provenance: what's official Anthropic/OpenAI vs. not
README.md at the repo root is the human-facing explanation of the same skill and
must stay consistent with skills/graph-engineer/SKILL.md — they describe the same
8-node cycle from two angles (marketing/usage vs. operational instructions). When
editing one, check whether the other needs a matching update (e.g. node numbering,
flag names, the anti-loop cutoff wording). Their section order is deliberately
different, though: README.md is ordered for reading (what is this → what does
the cycle look like → how do I use it → what can go wrong), while SKILL.md is
ordered for execution (node 0 through node 7 in sequence). Don't treat a
reordering of one as something that needs mirroring in the other — only the
claims need to match, not the layout.
Working in this repo
There is nothing to build, lint, or test. "Development" here means editing Markdown
(SKILL.md, README.md, the reference files) and keeping the following
consistent across all of them:
- The 8-node cycle order and names: PRE-FLIGHT → SPEC → IMPL → QUALITY GATE → CRITIQUE → DEBATE/TRIAGE → REFACTOR → VERIFY.
- The single entry point claim: every Codex interaction routes through the
codex:codex-rescuesubagent — no other/codex:*command is invoked programmatically by this skill. - The pinned plugin version (
openai-codexv1.0.6) that the routing assumptions were verified against. If that version changes,README.md,SKILL.md, andsources.mdall reference it and need to move together. Elevated assurance's fan-in barrier specifically depends on this version's--resume-lastsemantics (seesources.md's Verification method section) — a plugin update that adds resume-by-thread-ID could relax that barrier's requirements, but don't assume it without re-verifying the source.
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 · 131 lines · 1,910 tokens per session scan A ae4bf1fd1867
graph-engineer CLAUDE.md is an instructions file published in the GitHub repository Ranteck/graph-engineer (101 stars, last pushed 5d ago), licensed MIT. It adds 1,910 tokens to every session, about $0.0095 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to graph-engineer AGENTS.md, differing in 32 lines, and is treated as a copy.
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.