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/procoders/superpowers-v/agents-mdgit clone --depth 1 https://github.com/procoders/superpowers-vWhat 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 | $0.02842 | $0.02842 |
| Opus 5 | $0.01421 | $0.01421 |
| Sonnet 5 | $0.00568 | $0.00568 |
| Haiku 4.5 | $0.00284 | $0.00284 |
Grade A, and why
superpowers-v AGENTS.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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compound V — Codex / Universal Agent Shim (🧪 experimental, untested)
This file documents how the plugin's content would be consumed by tools that read AGENTS.md from a project root (Codex CLI and similar). It has not been tested on a real Codex install — tool-name mappings and dispatch syntax are based on documentation and may need adaptation per your harness version.
What this plugin does
Compound V is a sidekick to Superpowers. It intercepts the four Superpowers phase transitions (pre-brainstorm recon → brainstorming → writing-plans → execution) and adds:
- Gated pre-brainstorm recon (Trigger 0) 🧪 description-driven, with a reminder-only hook backstop (v2.8:
hooks/brainstorm-trigger0-nudge.shnudges when the Skill tool invokessuperpowers:brainstorming— a reminder, not enforcement; nothing can force the recon to run): before a brainstorm begins on an unfamiliar topic, a gated, bounded research pass (bundleddeep-researchif present, 3–6 parallel WebSearch otherwise, skip-with-notice if neither) writes an anti-anchoring recon doc todocs/superpowers/recon/that the brainstorm — and later pre-flights 1B/1C — read first. Gate order: plumbing-skip → V-memory KB hit →brainstorm.deep_researchconfig (askdefault /auto/offhard kill-switch). Recon is evidence, never a routing input. Also 🧪 description-driven: batched elicitation — ≥3 independent clarifying questions may batch into ONE screen via the surface ladder — Visual Companion form if accepted this session, else the harness's structured-question tool, else sequential (companion acceptance gates only the top surface); dependent chains stay sequential; when unsure → sequential; seeskills/compound-v/brainstorm-elicitation.md. - Three parallel pre-flights after brainstorming:
- Code archaeology (existing-code reality)
- Domain-expert advisor with three-layer audience search (product/regulatory reality)
- Library/doc validator via Context7 MCP (dependency currency)
- Disjoint File Partition Map enforcement inside writing-plans, which materializes a
manifest.yaml— the machine-readable contract that drives dispatch - Manifest-driven multi-backend dispatch (4-6 concurrent) on Opus by default, Sonnet only for strict junior-level mechanical tasks, or a headless Codex worker for large isolated builds
- A
git diffscope gate after every job — a worker that writes outside itswrite_allowedlist is BLOCKED and never merges; enforcement fields are git-derived, never model-self-reported - Crash-resume via a
state.jsonrun directory
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 · 111 lines · 2,842 tokens per session scan A be0c59844091
superpowers-v AGENTS.md is an instructions file published in the GitHub repository procoders/superpowers-v (35 stars, last pushed 2d ago), licensed MIT. It adds 2,842 tokens to every session, about $0.0142 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.
Other instructions, from other repositories
cezar AGENTS.md
Instructions for open-mercato/cezar, covering agents.md — working in this repository, zero config, changing a mechanism that already works, the http api and repository layout.
agentshield CLAUDE.md
Instructions for affaan-m/agentshield, covering agentshield, build & test, architecture, key patterns and severity scoring.
omniscribe CLAUDE.md
Instructions for Shironex/omniscribe, covering claude.md, project overview, requirements, commands and install dependencies.
exciton CLAUDE.md
Instructions for jspw/exciton, covering claude.md, what this is, commands, architecture and the interactive layer.
herdrpowers AGENTS.md
Instructions for transparent-pegasus/herdrpowers: This repository IS the herdrpowers plugin. The payload lives at the repo root: skills/ (16 skills), commands/ (6 workflows), docs/ (framework docs). Plugin manifests: .claude-plugin/, .codex-plugin/, .cursor-plugin/, .agents/plugins/marketplace.json.
ultrapowers CLAUDE.md
Instructions for 7xuanlu/ultrapowers, covering workflow, the engine and command are the product, treat them as such, after any edit and distribution.