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/cboone/agent-harness-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/cboone/agent-harness-plugins/review-until-clean)<a href="https://agentmods.dev/plugins/cboone/agent-harness-plugins/review-until-clean"><img src="https://agentmods.dev/badge/plugins/cboone/agent-harness-plugins/review-until-clean/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/cboone/agent-harness-plugins/review-until-clean"><img src="https://agentmods.dev/badge/plugins/cboone/agent-harness-plugins/review-until-clean.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
review-until-clean 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 2d 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.
What it actually says
{
"author": {
"name": "Christopher Boone"
},
"description": "Run a reviewer of your choice (a skill, slash command or CLI) over every local change, fix its findings at or above a severity threshold, and repeat until the exact snapshot on disk comes back clean or a round limit stops the loop.",
"homepage": "https://github.com/cboone/agent-harness-plugins",
"keywords": ["code-review", "loop", "pre-push", "review"],
"license": "MIT",
"name": "review-until-clean",
"repository": "https://github.com/cboone/agent-harness-plugins",
"skills": "./skills",
"version": "3.1.2"
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 25 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.
- 2d ago Changed 6899cb3b6094
- 3d ago Changed 3578f15d06f5
- 5d ago Changed 1b7b65aeebca
- 15d ago Changed 50c67c8acb51
- 18d ago First seen · 14 lines scan A cae984d2385d
review-until-clean is a plugin published in the GitHub repository cboone/agent-harness-plugins (2 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 2026-09-28.
Other plugins, from other repositories
app-store-review
Evaluates code against Apple's App Store Review Guidelines for iOS, macOS, tvOS, watchOS, and visionOS apps.
code-quality
Code quality pipeline — SOLID refactoring, TDD workflow, design patterns, performance optimization, and 6 specialist review agents.
diffscope
A Claude Code plugin that creates a learning brief immediately after the agent changes code. The brief shows what changed, explains Python syntax, and traces logic and data flow.
ghostty-notify
Native Ghostty desktop notifications for Claude Code (idle input / permission request / turn finished) via OSC 777. Per-tab suppression and click-to-focus are handled natively by Ghostty. Runs only under Ghostty.
tavs
Visual terminal state indicators for Claude Code sessions using OSC escape sequences. Changes background color and tab title based on Claude's state (processing, permission, idle, complete, compacting, subagent, toolerror).
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.