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 skills add alebgl77/claude-inc --skill superpowersgit clone --depth 1 https://github.com/alebgl77/claude-incWrote 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/skills/alebgl77/claude-inc/superpowers)<a href="https://agentmods.dev/skills/alebgl77/claude-inc/superpowers"><img src="https://agentmods.dev/badge/skills/alebgl77/claude-inc/superpowers/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alebgl77/claude-inc/superpowers"><img src="https://agentmods.dev/badge/skills/alebgl77/claude-inc/superpowers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00102 | $0.01059 |
| Opus 5.5 | $0.00041 | $0.00424 |
| Sonnet 5.5 | $0.00020 | $0.00212 |
| Haiku 4.5 | $0.00010 | $0.00106 |
Grade A, and why
superpowers 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 1mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Superpowers — Skill Forge
"14-skill power pack"
When to use
- End-to-end feature work that deserves discipline — "let's build this properly, not vibe-code it"
- A bug that resists poking — "debug this systematically", "it fails randomly and I'm lost"
- Pre-merge and pre-ship gates — "review my diff", "run a security pass", "are we ready to release?"
- After an incident — "write the postmortem"
- Any single phase named outright — spec it, plan it, refactor it, profile it, document it
The 14 protocols
| # | Protocol | Core move |
|---|---|---|
| P1 | Brainstorm | Generate 3+ approaches, score against constraints, pick one on the record. |
| P2 | Spec | Acceptance criteria and non-goals written before any code. |
| P3 | Plan | Ordered steps, each independently verifiable. |
| P4 | Scaffold | Skeleton with tooling wired — lint, test runner, entry point, CI hook. |
| P5 | TDD | Red-green-refactor: failing test first, minimal pass, then clean. |
| P6 | Systematic debugging | Reproduce → isolate → hypothesize → fix → regress. |
| P7 | Refactoring | Behavior-preserving change under green tests, one move at a time. |
| P8 | Code review | Line-level and design-level pass — correctness, security, perf, readability. |
| P9 | Performance pass | Measure first, profile the hot path, fix, re-measure. |
| P10 | Security pass | Inputs, authn/z, secrets, dependencies, injection surfaces. |
| P11 | Docs | README, API reference, runbook — written from the reader's seat. |
| P12 | Git hygiene | Small atomic commits, imperative messages, clean history. |
| P13 | Release checklist | Version, changelog, tests green, rollback plan, ship, verify live. |
| P14 | Postmortem | Blameless timeline, root cause, action items with owners. |
Workflow
- Identify the task's phase: idea, build, break/fix, ship, or learn.
- Pick the matching protocol(s) from the table and announce the pick — "Running P6 — systematic debugging."
- Execute the protocol as concrete steps. P6, for example: reproduce deterministically, isolate by bisecting code/data/env, state one falsifiable hypothesis, fix, add a regression test.
- For a full feature, chain: P1 → P2 → P3 → P4 → P5 → P8 → P11 → P12 → P13. Skip a link only by saying so and why.
- End every protocol with an artifact — spec file, failing-then-passing test, review notes, changelog — never just narrative.
- If the task changes phase mid-flight (the build surfaces a bug), switch protocols explicitly; don't blur two into mush.
- Log each run in the output format below and hand the next protocol its inputs.
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.
- 1mo ago First seen · 78 lines · 102 tokens per session scan A 40811176b8fe
superpowers is a skill published in the GitHub repository alebgl77/claude-inc (19 stars, last pushed 25d ago), licensed MIT. It adds 102 tokens to every session and 1,059 once invoked, about $0.0004 per session on Opus 5.5. 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 skills, from other repositories
code-review
Reviews code for bugs, security issues, and best practices.
java-code-review
Review Java code for bugs, duplicate code, correctness risks, maintainability improvements, and missing tests. By default review files modified in git; when the user explicitly names files, classes, packages, or a diff, review that scope instead. Generate a detailed review.md report with actionable comments and fixes.
spike-consumer-adversarial
OI-3 spike harness — heavy consumer, ADVERSARIAL arm. Worst-case early-exit test: the mid-workflow Skill call has no continuation guardrail and the guidance skill ends with a final-sounding anchor. Use only when explicitly invoked by the spike harness with a TRIALID and data path.
review
Review code changes, pull requests, patches, or a scoped code area for actionable correctness, security, compatibility, and test risks with file and line evidence. Use for review or audit requests; do not use for general proofreading, feature implementation, or debugging a reported failure when the user wants a fix.
debug
Diagnose a concrete failure, regression, crash, hang, flaky test, or incorrect runtime behavior by reproducing it, testing hypotheses, and identifying the evidence-backed root cause. Use when symptoms or failing output exist; do not use for feature implementation without a failure, general code review, or a conceptual…
adversarial-review
Run a file-audited completion loop that requires two consecutive fresh-context subagents to independently try to disprove the same versioned, digest-checked task result. Use when the user invokes $adversarial-review, asks for two independent adversarial approvals, or requires a result to survive repeated attempts to…