TPL_task_patterns

A template for designing agents that classifies work as research, implementation, content, operations, validation, or planning. It requires a final verification phase whose depth depends on task complexity.

In plain words
What is it for?
Use it when generating agents for research, system building, content creation, repeated operations, validation, or planning, especially when human-specified requirements must take priority.
Why use it?
It gives generated agents a consistent workflow and checks that they used the required inputs and produced results matching the task’s scope.

Agent

Install

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.

agentmods
npx agentmods add agents/miyatti777/ai-plc/tpl_task_patterns
Clone the repo
git clone --depth 1 https://github.com/miyatti777/ai-plc
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 932 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00932
Opus 5 $0.00000 $0.00466
Sonnet 5 $0.00000 $0.00186
Haiku 4.5 $0.00000 $0.00093

Measured 2d ago against content hash 9cfd68488992, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

TPL_task_patterns 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.

core/skills/ai-plc/templates/agents/TPL_task_patterns.md · 40 lines

What it actually says

🏷️ Type: template (meta) — Stage 3 Constructionがタスク種類を判定し、適切なPhase構造とAgentテンプレートを選択するためのメタパターン

タスク種類判定

種類 説明 必須出力 Agentテンプレート
research 調査・分析・リサーチ 分析レポート + 知見 TPL_research_agent
implementation DB作成・システム構築・実装 Databaseまたは動くシステム TPL_implementation_agent
content 記事執筆・プレゼン・ドキュメント 完成コンテンツ TPL_content_agent
operation 量産実行・パターン適用 量産成果物 + Evalデータ TPL_operation_agent
validation 検証・評価・レビュー 検証結果 + 改善計画 専用なし — research/implementationのPhaseに組み込み
planning 計画・ロードマップ・合意形成 確定計画 + コミット 専用なし — researchのPhaseに組み込み

共通原則(全Agent生成時に適用)

  1. HITL情報の拘束力 — Mob Checkpointやcontext.yamlで人間が明示指定した情報は「要件」として扱い、検索で見つかった類似情報より常に優先する
  2. 出力の検証 — Agent完了前に、指定インプットを実際に使用したか、出力がインプットの規模・範囲と整合しているかを確認する
  3. 出力エンティティの明確化 — 「Kanbanビュー/進捗管理」はDatabase+適切なビュー・プロパティ、「テンプレート/ガイド」はPageとして作る(ページ内の説明文・テーブルで代用しない)
  4. 「動くシステム」ルール — implementationタスクは実際に動くDatabase/システムを生み出さなければ完了としない(設計書だけでは不可)

汎用検証ステップ(全Agent共通 — system §18連動)

全Agent生成時、Execution Flowの最終フェーズに検証ステップを必ず含める。Adaptive深度と連動: Simple→L1のみ / Standard→L1+L2 / Complex→L1+L2+L3。

Level 名称 確認内容
L1 セクションチェック 各パーツが単体で正しいか(論理・根拠・欠落)
L2 統合チェック 全体の整合性(矛盾・流れ・トーン一貫性)
L3 受け手チェック 受け手が見て価値があるか(理解・アクション可能性)

検証タイミング: research=レポート完成後(セルフチェック+Mob)/ implementation=構築後(テスト実行+Mob)/ content=執筆後(セルフレビュー+Mobレビュー)/ operation=各量産サイクル後(Evalデータで自動判定)/ validation=検証自体が成果物のため不要。

Phase構造の標準パターン

パターン 構造 適用
A: Autonomous+Mob交互型 Autonomous → Mob → Autonomous → Mob → … 標準。AIが自動処理し要所で人間確認
B: エスカレーション型 設計 → Mob → DB作成 → ビュー追加 → データ投入 → Mob → ドキュメント implementation向け。段階的に成果物を構築
C: 量産実行型 変数バインド → Mob → Runtime Execution → Eval → 繰り返し operation(Production Run)向け
Changes

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.

  1. 2d ago First seen · 40 lines · 0 tokens per session scan A 9cfd68488992

Subscribe to this mod's changes

TPL_task_patterns is an agent published in the GitHub repository miyatti777/ai-plc (45 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 932 tokens. 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 2026-08-30.