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/ref-integrity-scannpx skills add s977043/PlanGate --skill ref-integrity-scangit 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/ref-integrity-scan)<a href="https://agentmods.dev/skills/s977043/plangate/ref-integrity-scan"><img src="https://agentmods.dev/badge/skills/s977043/plangate/ref-integrity-scan.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 | $0.00160 | $0.02084 |
| Opus 5 | $0.00080 | $0.01042 |
| Sonnet 5 | $0.00032 | $0.00417 |
| Haiku 4.5 | $0.00016 | $0.00208 |
Grade A, and why
ref-integrity-scan 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 4d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ref Integrity Scan
Provenance（出典・vendoring 規約）: growth-core
deletion-reference-scan（upstream: Growth-Teams-Agent@5219642 / 2026-07-03 時点）を PlanGate 向けに 汎用化して取り込み（#798）。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）。
ファイル・ディレクトリを削除・移動・改名する前後に、リポジトリ全体を対象に被参照（そのパスを指している箇所）を洗い出し、ダングリング参照を防ぐための手順スキル。
#691（check-stale-skill-refs.py）との相補関係
| スキル/スクリプト | 走査方向 | 検出対象 |
|---|---|---|
scripts/check-stale-skill-refs.py（#691） |
outbound（発信） | スキル/コマンド/エージェントが参照している先が実在しない（stale） |
| 本スキル（ref-integrity-scan） | inbound（被参照） | 削除・移動・改名する対象への参照が他のどこかに残っている |
#691 は「自分が指している先が消えていないか」、本スキルは「自分を消したときに誰かが迷子にならないか」を確認する。両方向を揃えることで参照整合を守る。
実害事例（動機）
2026-07-10、self-review スキルを diff-audit へ改名した際（#796）、削除・改名前の被参照スキャンを行わなかったため、以下が事後検出になった:
acceptance-reviewからのリンク切れ（RiverReview レビューで major 指摘として検出）.cursor配下の壊れた symlink（旧パスself-reviewを指したまま。Codex 側レビューで検出）
いずれも事前に inbound スキャンを行っていれば着手前に判明していた。本スキルはこの再発防止策として新設する。
When NOT to use
- コード内の import / require 参照の整合性チェック → 型チェッカー / linter を使う
- 外部サイトへのリンク切れ（http/https URL）のチェック → 対象外（本スキルはリポジトリ内参照のみ）
手順
Step 1: 対象パスの確認
削除・移動・改名する対象パスを列挙する（複数可）。例:
対象: .claude/skills/self-review/ (旧名)
対象: .claude/skills/self-review/SKILL.md
移動・改名の場合は「旧パス」と「新パス」の両方を把握しておく（新パスは対象外、旧パスのみスキャン対象）。
Step 2: スキャン実行
フルパスとファイル名のみの 2 パターンで grep する。参照形式が ./ 省略・相対パス表記・単純なファイル名参照など様々なため、片方だけでは取りこぼす。
対象ディレクトリ・ファイル: docs/ .claude/ .agents/ .codex/ .cursor/ plugin/ bin/ scripts/ CLAUDE.md AGENTS.md README*.md
対象拡張子: *.md *.json *.sh *.yaml *.yml
TARGET_FULL="path/to/target" # フルパス（削除・移動対象）
TARGET_NAME="$(basename "$TARGET_FULL")" # ファイル名のみ
# プレースホルダのまま実行すると全行マッチで大量出力になるためガードする
if [ -z "$TARGET_FULL" ] || [ "$TARGET_FULL" = "path/to/target" ]; then
echo "Error: TARGET_FULL を実際の対象パスに設定してください" >&2
else
# git grep は .gitignore を尊重し高速。--untracked で未コミットの新規ファイルも対象に含める
# パターン1: フルパスでの参照
git grep -n -F --untracked -- "$TARGET_FULL" -- '*.md' '*.json' '*.sh' '*.yaml' '*.yml'
# パターン2: ファイル名のみでの参照（誤検出が出やすいので手動で絞り込む）
git grep -n -F --untracked -- "$TARGET_NAME" -- '*.md' '*.json' '*.sh' '*.yaml' '*.yml'
fi
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.
- 4d ago First seen · 111 lines · 160 tokens per session scan A bf7cf0f389b6
ref-integrity-scan is a skill published in the GitHub repository s977043/PlanGate (2 stars, last pushed 4d ago), licensed MIT. It adds 160 tokens to every session and 2,084 once invoked, about $0.0008 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]…
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.
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.