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/kazuph/yunomiWrote 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/kazuph/yunomi/plugin)<a href="https://agentmods.dev/plugins/kazuph/yunomi/plugin"><img src="https://agentmods.dev/badge/plugins/kazuph/yunomi/plugin/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/kazuph/yunomi/plugin"><img src="https://agentmods.dev/badge/plugins/kazuph/yunomi/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
yunomi-plugin 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.
What it actually says
{
"name": "yunomi-plugin",
"version": "2.6.6",
"description": "yunomi development workflow: do, done, and bucho skills with code/security, E2E, UI/UX, and evidence review agents. Preserve existing functionality while carrying requested changes through verification and human approval. Supports web, backend, and mobile projects.",
"author": {
"name": "kazuph",
"url": "https://github.com/kazuph"
},
"homepage": "https://github.com/kazuph/yunomi",
"repository": "https://github.com/kazuph/yunomi",
"license": "MIT",
"keywords": [
"review",
"csv",
"markdown",
"diff",
"workflow",
"task-management",
"e2e-testing",
"code-review",
"backend-testing",
"mobile-testing",
"maestro"
]
}
What it installs
The manifest is a name and a version. 3 skills, 10 agents, 3 hooks travel with it, and installing the plugin installs all of them — 684 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill do A 22 tokens
- Skill done A 27 tokens
- Skill bucho A 28 tokens
- Agent mobile-impl A 92 tokens
- Agent report-builder A 27 tokens
- Agent review-e2e A 60 tokens
- Agent review-code-security A 57 tokens
- Agent backend-impl A 82 tokens
- Agent report-validator A 47 tokens
- Agent review-ui-ux A 55 tokens
- Agent webapp-impl A 87 tokens
- Agent dogfooding A 47 tokens
- Agent review-video C 53 tokens
- Hook PreToolUse A not measured
- Hook PostToolUse A not measured
- Hook UserPromptSubmit A not measured
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 Changed 45c8e8590789
- 1mo ago First seen · 26 lines scan A af14524c8f77
yunomi-plugin is a plugin published in the GitHub repository kazuph/yunomi (21 stars, last pushed 23d 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 2026-08-30.
Other plugins, from other repositories
convergo
Intent-driven planning, implementation and independent review with bounded repairs.
of-loop
Stable Claude Code adapter for the vendor-neutral OwnFramework Loop autonomous engineering runtime.
convergo
Intent-driven planning, implementation and independent review with bounded repairs.
han-communication
Foundational communication plugin for the Han suite. Owns the canonical readability standard, the writing-voice profile, and the explanation standard for talking to a reader who will not implement the work, plus the readability-guidance skill that surfaces the first two into a calling skill's own context for in-voice…
pedantic-coder
Zero-tolerance code pedantry — naming precision, casing law, structural symmetry, import discipline, and the obsessive details that separate clean code from correct code.
code-quality
OxLint, Biome, and Prettier configuration, linting skills, and pre-commit hooks for consistent code quality.