Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ncaq/konoka/plugin install kyoseiWrote 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/skills/ncaq/konoka/kyosei)<a href="https://agentmods.dev/skills/ncaq/konoka/kyosei"><img src="https://agentmods.dev/badge/skills/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/skills/ncaq/konoka/kyosei"><img src="https://agentmods.dev/badge/skills/ncaq/konoka/kyosei.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.05561 |
| Opus 5 | $0.00023 | $0.02780 |
| Sonnet 5 | $0.00009 | $0.01112 |
| Haiku 4.5 | $0.00005 | $0.00556 |
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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 504 lines — stays where its author put it; the contents beside it link to each section on GitHub.
コマンドの実行方法
このスキルはnode <プラグインルート>/dist/bin/*.js形式でヘルパーコマンドを実行します。
Claude Codeはコマンド例中の変数CLAUDE_PLUGIN_ROOTの参照を絶対パスへ展開しますが、
展開されず文字通りのまま残っている環境(OpenCodeなど)ではこの形式は動きません。
その場合は代わりにPATH上のget-review-infoとsubmit-reviewを同じ引数で実行してください。
get-review-infoでの情報の取得
以下のコマンドでレビューに必要な情報を取得して、 用途別のファイルに書き出します。
node ${CLAUDE_PLUGIN_ROOT}/dist/bin/get-review-info.js $ARGUMENTS
標準出力にはレビュー情報自体ではなく、
書き出したファイルの絶対パスを持つJSONが1行だけ返されます。
出力をtailやパイプなどで加工せず、
JSON全体をそのまま受け取ってください。
以下は出力例です。
{
"context": "/run/user/1000/coding-agent-work/kyosei/review-info-example/context.json",
"patch": "/run/user/1000/coding-agent-work/kyosei/review-info-example/changeset.patch",
"commits": "/run/user/1000/coding-agent-work/kyosei/review-info-example/commits.log",
"changesetMetadata": "/run/user/1000/coding-agent-work/kyosei/review-info-example/changeset-metadata.json",
"conversation": "/run/user/1000/coding-agent-work/kyosei/review-info-example/conversation.json",
"previousReview": "/run/user/1000/coding-agent-work/kyosei/review-info-example/previous-review.json",
"incrementalChangeset": "/run/user/1000/coding-agent-work/kyosei/review-info-example/incremental-changeset.json"
}
返されたパスのファイルをReadツールで直接読んでください。
レビュー情報を1つのJSONへ結合したり、
一部を取り出すためにシェルコマンドで加工したりしないでください。
パスJSONの解釈
context
context.jsonへのパスです。
context.outputフィールドで出力先を判別します。
"github"
GitHub出力。
結果はGitHub PRにインラインコメントとして投稿されます。
hostとpr(owner, repo, prNumber)が含まれます。
"local"
ローカル出力。
結果はターミナルに直接出力されます。
ブランチに紐付くPRが特定できた場合はprが含まれます。
patch
レビュー対象の差分をdiffフォーマットで保存したchangeset.patchへのパスです。
commits
コミットログを保存したcommits.logへのパスです。
changesetMetadata (headCommitIdが存在する場合のみ)
headCommitIdを保存したchangeset-metadata.jsonへのパスです。
主にGitHub出力時に含まれます。
conversation (PRが特定できた場合のみ)
PRの既存コメント・レビュー情報を保存したconversation.jsonへのパスです。
GitHub出力モードでは常に含まれます。
ローカル出力モードでもブランチに紐付くPRがあれば含まれます。
PRが特定できない場合はパスJSONから省略されます。
トップレベルにPR自体の情報(title, body, author, urlなど)があり、
以下の3つのサブフィールドがあります。
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.
- 9d ago First seen · 504 lines · 47 tokens per session scan A 0330704cf19d
kyosei is a skill published in the GitHub repository ncaq/konoka (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 47 tokens to every session and 5,561 once invoked, about $0.0002 per session on Opus 5. 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 skills, 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.
remember
Record why something is the way it is — a decision and its reasoning, a lesson that cost time, or a standing constraint. Use when the reasoning behind a choice would be expensive to reconstruct later.
pr-from-stale-branch-silently-reverts-newer-main-files
Trap: merging a PR whose branch carries an OLD TREE silently DELETES (reverts) files that landed on main after that tree was built — with NO merge conflict to warn you, because a deletion your own commit records is not a conflict. Use when: (1) about to gh pr create or squash-merge from a long-lived / earlier-branched…
parallel-pr-scope-overlap-tiebreaker-delta-check
Before applying a handoff prompt's tiebreaker default ("merge the first-mover", "the clean-against-main one", "the one with reviewer APPROVE") to pick a winner between two parallel PRs that implemented the SAME scope, run gh pr diff on BOTH and audit for substantive deltas. Use when: (1) a session prompt or handoff…
pr-plan-bucket-triage-before-sizing
Before writing detailed pull request plans against a codebase you have not audited, triage it by bucket so sizes rest on findings rather than assumptions.
code-review-subagent-fabricates-specifics-to-inflate-severity
When a code-review subagent (voltagent-qa-sec, opus-tier reviewer, code-reviewer, etc.) reports a HIGH or BLOCKING severity finding, verify any SPECIFIC EVIDENCE the reviewer cites (line numbers, call counts, exact function/symbol names, file paths beyond the obvious diff) BEFORE treating the severity as actionable.…