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/intent-classifiernpx skills add s977043/PlanGate --skill intent-classifiergit 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/intent-classifier)<a href="https://agentmods.dev/skills/s977043/plangate/intent-classifier"><img src="https://agentmods.dev/badge/skills/s977043/plangate/intent-classifier.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 | $0.00083 | $0.03308 |
| Opus 5 | $0.00042 | $0.01654 |
| Sonnet 5 | $0.00017 | $0.00662 |
| Haiku 4.5 | $0.00008 | $0.00331 |
Grade A, and why
intent-classifier scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent Classifier
正本（sync 元）:
.agents/skills/intent-classifier/SKILL.md。scripts/sync-plugin-plangate.shが.agents/skills/を読み取りplugin/plangate/skills/を機械生成する。.claude/skills/と.codex/skills/は sync 対象外の配布先のため、正本更新時に同一内容を手動で追従させる。
ユーザーの依頼文を読み取り、開発 Intent を 8 分類のいずれかに判定して structured JSON で返す。
参照解決順（.claude/rules/*.md / 導入先で必ずこの順に探す）
本 Skill は責務境界の説明として .claude/rules/mode-classification.md を参照する
（§責務境界）。このパスは上流リポジトリ基準のため、導入先では 次の順で探索する:
- 導入先リポジトリの
.claude/rules/mode-classification.md - 無ければ plugin root 配下
<plugin_root>/rules/mode-classification.md。<plugin_root>は Bash でls "${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」と明示し、 推測で内容を補わない
Iron Law
CLASSIFY BASED ON EXPLICIT SIGNALS, NOT ASSUMPTIONS
依頼文に存在しないシグナルで分類を変えてはならない。 曖昧な場合は confidence を下げて reasoning に根拠を示せ。
Common Rationalizations
| こう思ったら | 現実 |
|---|---|
| 「文脈から明らかだから confidence=1.0 でいい」 | 曖昧さは必ず confidence に反映しろ |
| 「どちらにも取れるが多分 feature だろう」 | 複数候補時は上位 2 件を candidates に列挙しろ |
| 「short な依頼文だから判定できない」 | 情報不足でも最良推定で判定し、confidence を下げる |
Intent 分類定義
| Intent | 説明 | キーワード例 |
|---|---|---|
feature |
新機能・新動作の追加 | 追加, 実装, 作成, 新しい, 追加してほしい |
bug |
既存機能の欠陥修正 | 直す, 修正, エラー, バグ, 壊れている, 失敗する |
refactor |
動作を変えずにコード構造を改善 | リファクタ, 整理, 整頓, 分割, 綺麗にする, 改善 |
research |
技術調査・設計調査・情報収集 | 調査, 調べる, 比較, 評価, どうすべきか, 方針 |
review |
コード・設計・ドキュメントのレビュー | レビュー, 確認, チェック, 問題ないか, 品質 |
docs |
ドキュメント・コメント・README の追加・更新 | ドキュメント, README, コメント, 説明, 記述 |
ops |
CI/CD・デプロイ・監視・インフラ・設定変更・PlanGate CLI 操作（render/approve/exec/doctor） | デプロイ, CI, CD, インフラ, 設定, 環境, リリース, render, HTML 確認, C-3 確認, C-3 HTML, approve, plangate render, plangate approve, doctor |
exploratory |
要件が未確定な探索的デバッグ・仮説検証ループ（「やってみて初めて問題が露呈する」タスク）→ WF-07 を推奨 | 探索, デバッグ, 原因不明, 試す, 仮説, 段階的に, 入れ子, ビルド失敗, 何度も失敗, 検証しながら |
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.
- 3d ago First seen · 200 lines · 83 tokens per session scan A 4db1681a124e
intent-classifier is a skill published in the GitHub repository s977043/PlanGate (2 stars, last pushed 3d ago), licensed MIT. It adds 83 tokens to every session and 3,308 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]…
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.