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/7xuanlu/ultrapowers/agents-mdgit clone --depth 1 https://github.com/7xuanlu/ultrapowersWrote 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/7xuanlu/ultrapowers/agents-md)<a href="https://agentmods.dev/instructions/7xuanlu/ultrapowers/agents-md"><img src="https://agentmods.dev/badge/instructions/7xuanlu/ultrapowers/agents-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 | $0.01620 | $0.01620 |
| Opus 5 | $0.00810 | $0.00810 |
| Sonnet 5 | $0.00324 | $0.00324 |
| Haiku 4.5 | $0.00162 | $0.00162 |
Grade A, and why
ultrapowers 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 5d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENT.md, operating manual for agents working on ultrapowers
Shared, tool-agnostic guidance for any coding agent (Claude Code, Codex, Gemini CLI, …) that
contributes to this repo. Claude Code imports it via CLAUDE.md. It is about building
ultrapowers itself, not about running the harness on a downstream project.
What this repo is
ultrapowers is a Claude Code Workflow, a deterministic JavaScript coordinator
(workflow/ultrapowers-development.js) that hosts Superpowers' SDD/TDD discipline on disposable
subagents: plan → per-task (implement under strict TDD → deterministic gate → re-witness-RED →
two-stage fail-closed review → fix-loop) → dry-until-clean critic → final integration review.
The coordinator makes zero LLM calls; all work tokens are paid by subagents. The
/workflows-driven-development command owns the two human gates and dispatches the engine, it
must never re-implement the loop.
The discipline bar (eat our own dog food)
This is a tool that gates other people's code on TDD and adversarial review. Contributions are held to the same bar.
- TDD where it applies, code/logic changes follow red → green → refactor. Write the failing test first, watch it fail, make it pass. Docs, JSON manifests, and CI YAML have no unit test; verify them by validity (parses / lints) and by reading, not by skipping verification.
- re-witness-RED is the headline mechanism, strip a task's production files, re-run the
suite, confirm it fails without them. Never weaken it. Its proof lives in
tests/re-witness-red/. - Surgical changes, touch only what the task needs; match existing style; no "while I'm here" refactors. No speculative surface (no flags/abstractions/error-handling beyond what's asked).
- Verify before claiming done, run
npm run check; for engine behavior, run the re-witness self-test. Evidence before assertions.
Verification commands
| command | what it does | cost |
|---|---|---|
npm run check |
parses the engine the way the runtime loads it (strips export, compiles as async IIFE) |
free, no deps |
npm run test:rewitness |
replays the re-witness-RED catch path through Claude Code | spends tokens / needs auth |
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.
- 5d ago First seen · 100 lines · 1,620 tokens per session scan A 62cc6279889d
ultrapowers AGENTS.md is an instructions file published in the GitHub repository 7xuanlu/ultrapowers (10 stars, last pushed 1mo ago), licensed MIT. It adds 1,620 tokens to every session, about $0.0081 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
superpowers-v AGENTS.md
AGENTS.md instructions for procoders/superpowers-v, covering requirements, what this plugin does, orchestrator surface (v1.0 + 1.1), v-memory recall surface (v2.0) and how codex / non-claude-code harnesses use it.
superpowers-v GEMINI.md
Gemini CLI instructions for procoders/superpowers-v, covering compound v — gemini cli shim (🧪 experimental, untested), what this plugin does, orchestrator surface (v1.0 + 1.1), v-memory recall surface (v2.0) and how gemini uses it.
superpowers-v CLAUDE.md
Claude Code instructions for procoders/superpowers-v, a project described as: Compound V — a multi-model orchestrator for Claude Code, layered on Superpowers: a deterministic router (Opus for risky work, Sonnet for the mechanical), cross-model review (Claude + Codex), 3 scouts (code · docs · domain), semantic memory…
exciton CLAUDE.md
Instructions for jspw/exciton, covering claude.md, what this is, commands, architecture and the interactive layer.
beads-superpowers CLAUDE.md
Instructions for DollarDill/beads-superpowers, covering beads-superpowers — agent instructions, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.
superpowers-cc-to-codex CLAUDE.md
Instructions for mzored/superpowers-cc-to-codex, covering claude.md, setup, plugin users, development and requirements.