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.
npx skills add s977043/PlanGate --skill plan-quality-checkgit clone --depth 1 https://github.com/s977043/PlanGateWrote 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/s977043/plangate/plan-quality-check)<a href="https://agentmods.dev/skills/s977043/plangate/plan-quality-check"><img src="https://agentmods.dev/badge/skills/s977043/plangate/plan-quality-check/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/s977043/plangate/plan-quality-check"><img src="https://agentmods.dev/badge/skills/s977043/plangate/plan-quality-check.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 | $0.00098 | $0.01103 |
| Opus 5 | $0.00049 | $0.00551 |
| Sonnet 5 | $0.00020 | $0.00221 |
| Haiku 4.5 | $0.00010 | $0.00110 |
Grade A, and why
plan-quality-check 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 7d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Quality Check
計画文書(目的・スコープ・成功条件・完了条件)を読み、品質を構造化して 返す軽量 Check の Skill。重い Gate / Agent orchestration / PR review / QA automation には依存しない(手動実行可能・補助情報)。
カテゴリ
Design
想定 Phase
計画レビュー前後の軽量確認(計画作成直後・実装着手前)
役割
3 種の Check を単独または統合(combined)で実行する:
| Check | 目的 | 主出力 |
|---|---|---|
plan_check |
目的・対象・成功条件・スコープの明確さを確認 | score / missing_items / summary |
risk_check |
失敗要因・依存関係・未決事項・暗黙の前提を確認 | risks / assumptions / next_actions |
done_check |
完了条件・検証方法・リリース後確認を確認 | done_criteria / validation_notes |
補足:
done_checkは**停止条件(completion / stop condition)の記述有無を、risk_checkは再計画トリガ(前提崩壊・逸脱を検知する定量条件)**の記述有無を確認観点に含める。いずれも汎用観点であり、具体のチェック項目はプロジェクト側テンプレート(例 review-self)で定義する。
補足2: high-risk / critical の実装タスクでは rollback(戻し手順)の記述有無を
done_checkの確認観点に含める。rollback 欠落は安全側(needs_clarification)に倒す。具体項目は review-self テンプレで定義(C1-TODO-RB)。 補足3(TASK-0129 / #543): Loop 安全制御チェックをdone_check/risk_check観点に追加する:
ID チェック内容 判定 C1-LOOP-01 plan に Stop Condition(停止条件)が記入されているか 未記入 → WARN(high-risk/critical ではFAIL)C1-LOOP-02 plan に Replan Triggers と機械値(閾値)が記入されているか 未記入 → WARN、機械値なし →WARN(high-risk/critical ではFAIL)これらは
#544/#551の Loop 安全制御(Phase1 検出)と連動し、 C-3 承認不可の strict Gate(Phase2)へ接続する(docs/ai/review-gate-decision-mapping.md§5 参照)。
入力
- 計画文書(目的 / スコープ / 受入基準 / 完了条件を含むテキスト)
- 任意: 確認したい Check 種別(plan_check / risk_check / done_check / combined)
出力
- 結果 JSON(
score,decision,summary,missing_items,risks,assumptions,done_criteria,next_actions, 任意score_breakdown,validation_notes) - 出力構造はリポジトリ側スキーマ(
schemas/plan-quality-check.schema.json) に準拠させる - 自由文サマリも併記してよいが、機械処理対象は JSON とする
Plan Health Score の考え方
0-100。最小内訳: goal_clarity / scope_defined / success_metric /
risks_identified / done_criteria_defined。閾値で助言的に
ready / needs_clarification / insufficient を返す。
制約
- 本 Check の
decisionは 助言であり、人間承認・ゲート判定の 代替にしない。 - 重い自動実行(PR review / browser QA / pair-agent)を呼び出さない。
- 不足が判定不能なときは安全側(より低い score / needs_clarification)。
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.
- 7d ago First seen · 69 lines · 98 tokens per session scan A 3b488e614891
plan-quality-check is a skill published in the GitHub repository s977043/PlanGate (2 stars, last pushed today), licensed MIT. It adds 98 tokens to every session and 1,103 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
skill-maintenance
Automated skill maintenance tool (v6 — Unified Registry + Snapshots). Full scan: [Orphan] migrate misplaced skills from category dirs OR standalone skills/<name>/ to auto-generated/, [Sync] auto-generated/ vs registry lifecycle diff (new/deleted/revived + description auto-sync via lifecycle field), [Reg]…
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
review
5-pass structured code review — correctness, security, performance, readability, consistency.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.