Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/s977043/PlanGatenpx agentmods add skills/s977043/plangate/plan-normalizationWrote 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-normalization)<a href="https://agentmods.dev/skills/s977043/plangate/plan-normalization"><img src="https://agentmods.dev/badge/skills/s977043/plangate/plan-normalization/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-normalization"><img src="https://agentmods.dev/badge/skills/s977043/plangate/plan-normalization.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 | $0.00092 | $0.03482 |
| Opus 5.5 | $0.00037 | $0.01393 |
| Sonnet 5.5 | $0.00018 | $0.00696 |
| Haiku 4.5 | $0.00009 | $0.00348 |
Grade A, and why
plan-normalization 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.
How it starts
The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Normalization
レビュー履歴を追記した Plan を、現在の最終合意状態だけで自己完結する Canonical Plan に再構成する。
重要: PlanGate は C-3 で plan_hash を固定し、exec 時に EH-3 が照合する。したがって正規化は C-3 承認前に行う。C-3 後の plan.md 書き換えは禁止。
適用位置
C-2 external review
↓
R-NNN 確定反映
↓
Plan Normalization ← 本 skill
↓
簡易 C-1 再実行
↓
C-3 human approval / plan_hash 固定
↓
exec
適用範囲（この Gate が掛かる対象）
本 Gate は これから normalization を通す Plan にだけ適用する。既存の
docs/working/TASK-XXXX/plan.md 全体を後から一括で検査する lint ではない。
| 対象 | 扱い |
|---|---|
| 本 skill を通して正規化する Plan（C-2 反映後・C-3 前） | 適用（checker 必須） |
| 既に C-3 承認済み / 完了済みの過去 Plan | 対象外（遡って是正しない。C-3 後の書き換えは plan_hash を壊すため禁止） |
| C-2 を実施せず修正履歴も無い light / ultra-light の Plan | N/A（実施しない。ただし C-1 / C-3 の既存条件は緩和しない） |
理由: checker の必須見出しは docs/working/templates/plan.md 系の Canonical
Plan 構造を前提としており、過去に別テンプレートで書かれた Plan は構造的に
一致しない。既存資産を一括で違反判定にしないため、適用対象を「正規化を通す
Plan」に限定する。過去 Plan を canonical 化したい場合は、その Plan を本 skill
に通す時点で初めて対象になる。
Read First
docs/working/TASK-XXXX/plan.mddocs/working/TASK-XXXX/pbi-input.mddocs/working/TASK-XXXX/test-cases.mddocs/working/TASK-XXXX/todo.mddocs/working/TASK-XXXX/review-external.md（存在すれば）docs/working/TASK-XXXX/review-self.mddocs/working/TASK-XXXX/decision-log.jsonldocs/ai/plan-normalization-gate.md（上流リポジトリで参照可能な場合。本 Skill が正本であり、当該 docs は上流向けの概要と入口）
参照解決順（
docs/**/ 導入先で必ずこの順に探す）: 本 Skill が参照するdocs/**は上流リポジトリ基準の相対パスであり、install.sh --claude/ plugin（Claude marketplace）/ Codex の 3 経路とも配布対象外（解決不可）。(1) 導入先リポジトリの同名パスを探す → (2) 見つからなければ 「正本<path>を参照できなかった」と明示し、本 Skill 内の記述を代替正本として扱い、推測で内容を補わない。plugin root 配下の探索はdocs/**には適用しない: plugin が配布するのはagents/commands/skills/rules等の定義ディレクトリのみでdocs/を配布対象として認識せず、plugin root 配下に相当する配布物が存在しないため、plugin root 段を置いても必ず空振りする（クラス A の rules 参照が plugin root 配下で解決できるのはrules/が実際に配布されるからであり、この非対称をdocs/**に持ち込まない）。
出力契約
正規化後も成果物の正本は plan.md のままとする。canonical-plan.md を別に増やさない。
理由:
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 · 251 lines · 92 tokens per session scan A 40d782f2c4df
plan-normalization is a skill published in the GitHub repository s977043/PlanGate (2 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 3,482 once invoked, about $0.0004 per session on Opus 5.5. 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]…
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.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
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.