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 Peiiii/nextclaw --skill superpowersgit clone --depth 1 https://github.com/Peiiii/nextclawWrote 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/peiiii/nextclaw/superpowers)<a href="https://agentmods.dev/skills/peiiii/nextclaw/superpowers"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/superpowers.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 | $0.00043 | $0.01671 |
| Opus 5 | $0.00022 | $0.00835 |
| Sonnet 5 | $0.00009 | $0.00334 |
| Haiku 4.5 | $0.00004 | $0.00167 |
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 3d 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Superpowers
Overview
Use this skill when the user wants a stronger engineering workflow inside NextClaw.
This marketplace skill adapts the upstream obra/superpowers project into a single installable NextClaw skill. Because NextClaw marketplace installs one skill directory at a time, this package provides:
- one top-level workflow router,
- bundled local reference files for the most useful upstream superpowers skills,
- and clear rules for when to load which reference.
Be explicit about the boundary:
- This skill owns workflow selection, expectation-setting, and reference routing.
- The bundled reference files own the detailed superpowers methodology.
- NextClaw, the current project rules, and the actual tool runtime own execution.
Do not present bundled superpowers guidance as a higher-priority authority than the user's instructions, the current project's AGENTS.md, or the host platform's rules.
What This Skill Covers
- design-first brainstorming before implementation,
- implementation plan writing for multi-step work,
- test-driven development for feature and bugfix work,
- root-cause-first debugging,
- pre-merge or post-task code review prompts,
- evidence-before-claims verification,
- optional subagent-driven execution when the environment actually supports it.
What This Skill Does Not Cover
- overriding user instructions or project rulebooks,
- pretending NextClaw natively supports the upstream superpowers multi-directory auto-discovery model,
- forcing subagent workflows when the current runtime does not support them,
- claiming a workflow step happened when the needed evidence was not actually collected,
- replacing domain-specific project skills that are more specific than this general workflow skill.
Install Boundary
Always distinguish these paths:
- NextClaw marketplace install:
nextclaw skills install superpowers - Installed NextClaw skill assets:
<workspace>/skills/superpowers/ - Upstream standalone installation outside NextClaw:
clone
https://github.com/obra/superpowersand follow the upstream install docs
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- marketplace.json 2.0 KB
- references/brainstorming.md 10 KB
- references/requesting-code-review.md 2.9 KB
- references/SOURCES.md 1.6 KB
- references/subagent-driven-development.md 12 KB
- references/systematic-debugging.md 9.7 KB
- references/test-driven-development.md 9.6 KB
- references/verification-before-completion.md 4.1 KB
- references/writing-plans.md 5.9 KB
- UPSTREAM_LICENSE 1.0 KB
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.
- 3d ago First seen · 219 lines · 43 tokens per session scan A 792a132ca541
superpowers is a skill published in the GitHub repository Peiiii/nextclaw (256 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 1,671 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
ai-agents-validation-and-qa
What counts as evidence in ai-agents and how to produce it. Covers the TESTING-RIGOR pos+neg+edge bar, test layout and collection reality, coverage proof commands, runtime-contract tests with negative controls, and ADR-034 QA skip semantics at session end. Use when you say what counts as evidence, how do I test this…
test-first
Use when implementing any feature, bugfix, or refactor that has a testable outcome. Activate for keywords like "TDD", "test-first", "red-green", "write the test first", "implement ", "fix ". Enforces the red-green-refactor discipline -- write a failing test, make it pass with the smallest change, refactor with tests…
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
incremental-tdd
Test-driven development with a strict red-green-refactor loop, vertical slices, and deep modules. Use to build features or fix bugs using TDD.
aetox-testing
ออกแบบกลยุทธ์และแผนทดสอบ, testing pyramid, กลยุทธ์รายชั้น (API, data pipeline, frontend, infra), จัดลำดับ critical path/edge/security บวกวินัย TDD (red-green-refactor) และกับดักเทสต์ที่ควรเลี่ยง ทริกด้วย "ควรเทสต์ยังไง", "test plan", "เขียนเทสต์ให้".
promptfoo-evaluation
Configures and runs LLM evaluation using Promptfoo framework. Use when setting up prompt testing, creating evaluation configs (promptfooconfig.yaml), writing Python custom assertions, implementing llm-rubric for LLM-as-judge, or managing few-shot examples in prompts. Triggers on keywords like "promptfoo", "eval", "LLM…