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/ncaq/konokaWrote 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/ncaq/konoka/kyosei)<a href="https://agentmods.dev/plugins/ncaq/konoka/kyosei"><img src="https://agentmods.dev/badge/plugins/ncaq/konoka/kyosei/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/ncaq/konoka/kyosei"><img src="https://agentmods.dev/badge/plugins/ncaq/konoka/kyosei.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
kyosei 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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "kyosei",
"version": "3.6.0",
"description": "Code review for PRs or local changes. Covers code quality, dependency updates, performance, test coverage, documentation accuracy, and security.",
"dependencies": ["research"],
"author": {
"name": "ncaq",
"email": "[email protected]",
"url": "https://github.com/ncaq"
},
"homepage": "https://github.com/ncaq/konoka/tree/master/plugins/kyosei",
"repository": "https://github.com/ncaq/konoka",
"license": "Apache-2.0",
"keywords": [
"dependencies",
"documentation",
"performance",
"quality",
"review",
"security",
"test"
]
}
What it installs
The manifest is a name and a version. 7 skills, 2 hooks travel with it, and installing the plugin installs all of them — 413 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill kyosei A 47 tokens
- Skill security-reviewer A 82 tokens
- Skill code-quality-reviewer A 56 tokens
- Skill dependency-reviewer A 24 tokens
- Skill documentation-reviewer A 66 tokens
- Skill performance-reviewer A 72 tokens
- Skill test-reviewer A 66 tokens
- Hook PreToolUse A not measured
- Hook SessionStart 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 First seen · 25 lines scan A ea354064eb64
kyosei is a plugin published in the GitHub repository ncaq/konoka (3 stars, last pushed yesterday), licensed Apache-2.0. 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
code-review
Code review practices with technical rigor and verification gates. Use for receiving feedback, requesting code-reviewer subagent reviews, or preventing false completion claims in pull requests.
architecture-review
Audits existing system architecture for anti-patterns, scalability risks, and reliability gaps. Produces graded findings with migration roadmap.
best-practices
Holistic codebase audit that auto-detects the stack and produces a prioritized improvement roadmap with level-of-effort estimates.
code-review
Structured engineering code review covering readability, complexity, test gaps, SOLID principles, and API consistency.
rust-intel
Defense against LLM Rust failure modes: 59 categories of bugs that survive rustc, clippy, and cargo test — async cancellation, unsafe/FFI, concurrency, crypto, supply-chain, tests-that-pass-by-luck, semantic conformance, and systemic performance cost. Ships the rust-intel skill plus /rust-intel:audit, /rust-intel:fix.
swarm-skill
Multi-agent codebase audit skill for Claude Code — spawns parallel subagents (security, performance, tests, architecture, dead-code) and synthesizes their findings into a prioritized action plan.