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/aiocean/claude-pluginsWrote 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/aiocean/claude-plugins/aio-perfectize)<a href="https://agentmods.dev/plugins/aiocean/claude-plugins/aio-perfectize"><img src="https://agentmods.dev/badge/plugins/aiocean/claude-plugins/aio-perfectize/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/aiocean/claude-plugins/aio-perfectize"><img src="https://agentmods.dev/badge/plugins/aiocean/claude-plugins/aio-perfectize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
aio-perfectize 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 yesterday.
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.
What it actually says
{
"name": "aio-perfectize",
"description": "Take finished, already-good work (code, prose, plans, analysis, UI) toward its best achievable form. Deletion test first, every edit a challenger the incumbent must lose to, an exemplar-derived bar that rises each cycle, and a fixed-point report that lists what could not be verified.",
"version": "1.0.1",
"author": {
"name": "aiocean"
},
"license": "MIT"
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 99 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- yesterday First seen · 10 lines scan A 13b1d4388809
aio-perfectize is a plugin published in the GitHub repository aiocean/claude-plugins (4 stars, last pushed 2d ago), licensed MIT. 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 2026-10-26.
Other plugins, from other repositories
ralph-wiggum
Implementation of the Ralph Wiggum technique - continuous self-referential AI loops for interactive iterative development. Run Claude in a while-true loop with the same prompt until task completion.
claudekit
Verification-first engineering toolkit for Claude Code. 15 skills across a 5-phase spine (Investigate → Design → Implement → Verify → Ship), 8 specialist agents, an interactive setup wizard. Every skill has rationalizations + evidence requirements. Built for senior ICs and tech leads.
navigator
Finish What You Start - Sessions that last, AI that learns, Features that ship. Context engineering + Theory of Mind + Knowledge Graph + Loop Mode + Task Mode. Features Project Knowledge Graph (unified search, experiential memory), unified workflow orchestration, auto-update on session start, ToM-based verification…
valet
Park a follow-up while Claude works — captured before it reaches the model, zero tokens — then pull it back with a native picker when you're ready.
ccbeep
Zero-dependency sound notifications for Claude Code. Plays audible alerts via PermissionRequest and Stop hooks — know when Claude needs approval or has finished, without watching the terminal. macOS / Linux / Windows.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.