superpowers-v CLAUDE.md

Project instructions for Superpowers Compound V, a system that routes work between AI models and uses code, documentation, and domain research assistants.

In plain words
What is it for?
Use them when onboarding to the repository, choosing models for tasks, consulting architecture documentation, or refreshing the project’s stored knowledge.
Why use it?
They explain the project’s architecture, coding conventions, model choices, and memory commands so agents can work within its established process.

Instructions file

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/procoders/superpowers-v/claude-md
Clone the repo
git clone --depth 1 https://github.com/procoders/superpowers-v
Per session 258 This file is loaded in full into every session.
When invoked 258 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 $0.00258 $0.00258
Opus 5 $0.00129 $0.00129
Sonnet 5 $0.00052 $0.00052
Haiku 4.5 $0.00026 $0.00026

Measured yesterday against content hash b44b78dd990e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

superpowers-v 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 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.

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 · 20 lines

What it actually says

@AGENTS.md

Claude Code

  • Architecture knowledge base (generated, citation-verified): docs/superpowers/architecture/ (architecture.md, business-logic.md, tech-context.md).
  • Repo conventions delta: CONVENTIONS.md (root).
  • Model policy: Opus by default, Sonnet for the narrow junior-task carve-out, never Haiku (enforced by scripts/lint-frontmatter.py and CI).
  • Recall over docs/superpowers/**: /v:remember <query>; re-index with /v:memory-refresh.
  • These docs are generated by /v:onboard; refresh with /v:onboard --refresh.
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. yesterday First seen · 20 lines · 258 tokens per session scan A b44b78dd990e

Subscribe to this mod's changes

superpowers-v CLAUDE.md is an instructions file published in the GitHub repository procoders/superpowers-v (35 stars, last pushed 2d ago), licensed MIT. It adds 258 tokens to every session, about $0.0013 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.