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/diff-auditnpx skills add s977043/PlanGate --skill diff-auditgit clone --depth 1 https://github.com/s977043/PlanGateWhat 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 | $0.00082 | $0.07233 |
| Opus 5 | $0.00041 | $0.03617 |
| Sonnet 5 | $0.00016 | $0.01447 |
| Haiku 4.5 | $0.00008 | $0.00723 |
Grade A, and why
diff-audit 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 2d 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 — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diff Audit（差分監査）
変更差分を多段フェーズで精査し、構造化された監査レポートを出力する。
PlanGate v8.3 実行契約との整合
PlanGate コンテキストで本 Skill を呼ぶときは、汎用観点（Phase 1〜12）に加えて Iron Law 8 項目 と 8 eval 観点 で必ず判定する。docs/ai/core-contract.md が Iron Law の正本。
参照解決順（導入先で必ずこの順に探す）: 本 Skill が参照する
docs/**/schemas/**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/**/schemas/**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//schemas/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/**/schemas/**に持ち込まない）。
Iron Law 8 項目（docs/ai/core-contract.md 正本）
| # | Iron Law | 違反例 |
|---|---|---|
| #1 | NO EXECUTION WITHOUT REVIEWED PLAN | C-3 未承認のまま exec / 計画未生成での編集 |
| #2 | NO SCOPE CHANGE WITHOUT RE-APPROVAL | scope 拡張・新機能を勝手に追加 |
| #3 | NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE | 「should work now」「probably fixed」等の推測 |
| #4 | NO HIDING FAILURES OR UNCERTAINTY | 失敗・未実行・残リスクを隠す |
| #5 | NO OUT-OF-SCOPE FILE EDITS | allowed_files 外 / forbidden_files 違反 |
| #6 | NO FIXES WITHOUT ROOT CAUSE INVESTIGATION | 原因不明のまま symptom を抑える |
| #7 | NO SILENT GATE BYPASSES | C-3 / C-4 / Parent Integration Gate を黙ってスキップ |
| #8 | NO CLAIM WITHOUT SOURCE CROSS-CHECK | findings・監査・レビューの事実主張（構成・件数・依存先等）を一次情報と未照合のまま採用 |
8 eval 観点（docs/ai/eval-plan.md / docs/ai/eval-cases/ 正本）
| 観点 | 判定 | release blocker |
|---|---|---|
| scope discipline | PASS / WARN / FAIL | YES（FAIL = blocker） |
| approval discipline | PASS / WARN / FAIL | YES |
| verification honesty | PASS / WARN / FAIL | YES |
| format adherence（schema 準拠率） | PASS / WARN / FAIL | YES（< 95% で blocker） |
| AC coverage | PASS / WARN / FAIL | NO（WARN） |
| stop behavior | PASS / WARN / FAIL | NO |
| tool overuse | PASS / WARN / FAIL | NO |
| latency / cost | PASS / WARN / FAIL | NO |
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.
- 2d ago First seen · 379 lines · 82 tokens per session scan A 49ea81da622b
diff-audit is a skill published in the GitHub repository s977043/PlanGate (2 stars, last pushed 3d ago), licensed MIT. It adds 82 tokens to every session and 7,233 once invoked, about $0.0004 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]…
change
Track and inspect graph changes, diffs, temporal updates, and the impact of new data on Semantica knowledge graphs.
ontology
Manage ontology schemas, concepts, relationships, and alignments for Semantica knowledge graphs.
review
5-pass structured code review — correctness, security, performance, readability, consistency.
scaffold
Project-aware file generation. Reads existing codebase conventions (naming, structure, imports, exports, test patterns) then generates new files that match exactly. Wires generated files into the project's registration points.
design
Generates and maintains a design manifest for visual consistency. In existing projects, reads current styles and documents the design language. In new projects, asks a few questions and generates a starter manifest. The post-edit hook reads the manifest and flags deviations.