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 agentmods add skills/s977043/plangate/breakdown-gatenpx skills add s977043/PlanGate --skill breakdown-gategit 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/breakdown-gate)<a href="https://agentmods.dev/skills/s977043/plangate/breakdown-gate"><img src="https://agentmods.dev/badge/skills/s977043/plangate/breakdown-gate.svg" alt="Measured on agentmods" 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 | $0.00143 | $0.02581 |
| Opus 5 | $0.00072 | $0.01290 |
| Sonnet 5 | $0.00029 | $0.00516 |
| Haiku 4.5 | $0.00014 | $0.00258 |
Grade A, and why
breakdown-gate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Breakdown Gate
Provenance（出典・vendoring 規約）: growth-core
task-breakdown-gate（upstream: Growth-Teams-Agent@5219642 / 2026-07-03 時点）を PlanGate 向けに 汎用化して取り込み（#799）。上流への自動追従はしない — 上流更新の反映は 意図的に diff をレビューして行う（provenance 追跡 + 意図的更新の vendoring 標準）。
実装着手前にタスクの粒度を判定し、粗すぎる場合は分割候補を提示する intake ゲート。growth-core task-breakdown-gate から蒸留。
参照解決順（導入先で必ずこの順に探す）
本スキルは規模判定の正本として .claude/rules/mode-classification.md を参照する
（本文中 3 箇所）。このパスは上流リポジトリ基準のため、導入先では 次の順で探索する:
- 導入先リポジトリの
.claude/rules/mode-classification.md。 ただし 本 skill が参照する節（例:mode-classification.mdの「判定基準」節）が実在することを確認する。同名でも別内容なら PlanGate の正本ではないため 2 へ進む - 無ければ plugin root 配下
<plugin_root>/rules/mode-classification.md。<plugin_root>は Bash でls "${CLAUDE_PLUGIN_ROOT}/rules/"を実行して展開・確認した 絶対パス（Read ツールは絶対パスを要求し環境変数を展開しないため、${CLAUDE_PLUGIN_ROOT}/...という文字列をそのまま Read しない）。変数が空・未設定ならキャッシュを glob で推測せず 3 へ進む - どちらにも無い場合は 「正本
mode-classification.mdを参照できなかった」と明示する。 本スキルは mode を決めないため判定自体は続行できる — 出力フォーマットの常設行**Mode 判定の正本**: 参照可 / 未参照（理由）に「未参照（<探した path>が どちらにも無い）」と記録し、5 段階 mode の内容を推測で補わない。 この行は分割要否に関わらず必ず出力する（「分割候補」は分割必要時のみ出る節のため、 記録先にしない）
| 参照 | install.sh --claude 経由 |
plugin（Claude marketplace）経由 | Codex 経由 |
|---|---|---|---|
rules/*.md |
.claude/rules/ に着地（解決可） |
<plugin_root>/rules/ で解決 |
未配置（解決不可 → 手順 3 へ） |
install.sh --claude のコピー対象は agents / skills / commands / rules の 4 ディレクトリ
のみ。Codex 経由（install_codex()）は install-plangate-skills.sh を呼ぶだけで skills しか
配置されないため、rules 参照は解決順 1・2 とも成立せず必ず手順 3 に落ちる。
Iron Law
ONE TASK = ONE PURPOSE, ONE PR-SIZED DIFF, ONE VERIFIABLE OUTCOME
目的・差分・検証結果のどれか 1 つでも複数に見えたら分割を検討する。
役割分界（オーガナイザー設計 / issue #799）
| 段階 | 担当 | 本スキルとの関係 |
|---|---|---|
| 起動前 intake | breakdown-gate（本スキル） | 5 要素 + 粒度判定 → 分割候補提示 |
| 起動後の規模判定 | .claude/rules/mode-classification.md（正本・不変。解決順は上記「参照解決順」） |
本スキルは mode を決めない（判定基準は参照のみ） |
| plan 生成後の粒度検査 | C-1 ToDo チェック「タスク粒度」（不変） | 本スキルは plan 生成前 |
| 規模 L 以上の MVP scoping | codex-mvp-split（既存・.agents/skills/codex-mvp-split/） |
本スキルは分割要否の判定まで。規模 L 以上と判明したら codex-mvp-split で最小 MVP（Phase 1）分割へ |
| plan 生成後の品質スコア | plan-quality-check（既存・.claude/skills/ 専用） |
5 要素は同系だがタイミングが異なる（本スキル=plan 前 / plan-quality-check=plan 後）。チェックリストの正本は各自 — 変更時は相互参照 |
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.
- 5d ago First seen · 135 lines · 143 tokens per session scan A 00e1f79fad7a
breakdown-gate is a skill published in the GitHub repository s977043/PlanGate (2 stars, last pushed 4d ago), licensed MIT. It adds 143 tokens to every session and 2,581 once invoked, about $0.0007 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
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…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
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.
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.