Borrowing it
Nothing to install: this file belongs to RonMizrahi/superpowers-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/RonMizrahi/superpowers-graph/main/CLAUDE.mdgit clone --depth 1 https://github.com/RonMizrahi/superpowers-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/ronmizrahi/superpowers-graph/claude-md)<a href="https://agentmods.dev/instructions/ronmizrahi/superpowers-graph/claude-md"><img src="https://agentmods.dev/badge/instructions/ronmizrahi/superpowers-graph/claude-md.svg" alt="Measured on agentmods" 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 | $0.00738 | $0.00738 |
| Opus 5 | $0.00369 | $0.00369 |
| Sonnet 5 | $0.00148 | $0.00148 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
superpowers-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 7d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
superpowers-graph — repository guide
One plugin, plugins/superpowers-graph/: the Superpowers methodology expressed as a guarded state
machine. 21 nodes · 96 guarded edges · 9 bounded cycles · 19 declared human stops.
This repo is a worked example of sdlc-graph-engineering — Ron Mizrahi's own project.
That plugin supplies the method (the nine-step transformation, the failure-mode catalogue, the
dry-trace-before-shipping rule, the eval contract); this repo is its output pointed at somebody
else's process. When the method and this graph disagree, the method is the thing worth fixing —
a defect found here is usually a gap in the transformation, not a one-off.
Sources of truth
skills/superpowers-graph/references/edges.md— the transition table. Authoritative for every guard. Where another file disagrees, this one wins and the other is the defect.references/nodes.md— the 21 node contracts.references/state.md— the run-state schema.SKILL.md— the orchestrator. It is an index: procedure lives inreferences/, not in it.references/*-node.md— seven copies trimmed from upstream superpowers, each carrying acopied-from: … @ v6.2.0header.
Changing the graph — the eval ships with the change
python3 plugins/superpowers-graph/skills/superpowers-graph/evals/run_all.py
A PostToolUse hook runs that after any Edit or Write under plugins/superpowers-graph/, so
drift returns as feedback on the edit that caused it. A red suite mid-change is expected — it is the
second half of the edit, not an error.
A graph change is not finished until it adds or updates the eval that would have caught its
absence. The full contract — fixture format, when a probe is legitimate, the negative-control
rule — is in evals/EVAL-INSTRUCTIONS.md. Read it before adding an eval. In short: a new edge
needs a walk that traverses it (enforced — coverage is a gate), a new invariant needs a check, a new
or changed stop needs both plus a planted violation in a negative control. A suite that cannot
fail is not evidence.
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.
- 7d ago First seen · 48 lines · 738 tokens per session scan A 8f091d60090b
superpowers-graph CLAUDE.md is an instructions file published in the GitHub repository RonMizrahi/superpowers-graph (1 stars, last pushed 1mo ago), licensed MIT. It adds 738 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 2026-08-31.
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.
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.
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 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
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.