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.
git clone --depth 1 https://github.com/caoguanjie/codepluginsWrote 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/plugins/caoguanjie/codeplugins/superpowers)<a href="https://agentmods.dev/plugins/caoguanjie/codeplugins/superpowers"><img src="https://agentmods.dev/badge/plugins/caoguanjie/codeplugins/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/plugins/caoguanjie/codeplugins/superpowers"><img src="https://agentmods.dev/badge/plugins/caoguanjie/codeplugins/superpowers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What it installs
The manifest is a name and a version. 14 skills, 3 commands, 1 agent, 1 hook travel with it, and installing the plugin installs all of them — 671 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill writing-skills A 20 tokens
- Skill subagent-driven-development A 17 tokens
- Skill systematic-debugging A 21 tokens
- Skill test-driven-development A 17 tokens
- Skill dispatching-parallel-agents A 26 tokens
- Skill receiving-code-review A 38 tokens
- Skill using-git-worktrees A 35 tokens
- Skill finishing-a-development-branch A 44 tokens
- Skill using-superpowers A 29 tokens
- Skill verification-before-completion A 43 tokens
- Skill writing-plans A 21 tokens
- Skill brainstorming A 37 tokens
- Skill executing-plans A 22 tokens
- Skill requesting-code-review A 22 tokens
- Command brainstorm A 30 tokens
- Command execute-plan A 7 tokens
- Command write-plan A 8 tokens
- Agent code-reviewer A 234 tokens
- Hook SessionStart A not measured
What ships with it
1 file beside plugin.json 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.
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 · 14 lines scan A 4d9b758c3f57
superpowers is a plugin published in the GitHub repository caoguanjie/codeplugins (7 stars, last pushed 8mo ago), with no licence file. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
superpowers
Core skills library: TDD, debugging, collaboration patterns, and proven techniques.
superpowers-zh
A Chinese-language collection of working methods for AI-assisted programming, including test-driven development, debugging, and code review. Test-driven development, or TDD, means writing tests before the code they check.
aegis
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques.
debugging
Debug observed failures via a disciplined six-phase loop: build a fast deterministic reproduction signal, reproduce, rank falsifiable hypotheses, instrument, fix with a regression test, then clean up and post-mortem.
superpowers-zh
A Chinese-language collection of practical methods for AI-assisted programming, including test-driven development, debugging, and code review. Test-driven development, or TDD, means writing tests before the code they are meant to check.
mattpocock-skills
mattpocock-skills. Skills for Real Engineers. Straight from my .claude directory. (github/mattpocock).