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 agents/satoh-y-0323/claude-code-conductor/plannergit clone --depth 1 https://github.com/satoh-y-0323/claude-code-conductorWrote 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/agents/satoh-y-0323/claude-code-conductor/planner)<a href="https://agentmods.dev/agents/satoh-y-0323/claude-code-conductor/planner"><img src="https://agentmods.dev/badge/agents/satoh-y-0323/claude-code-conductor/planner.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 | $0.00033 | $0.01344 |
| Opus 5 | $0.00016 | $0.00672 |
| Sonnet 5 | $0.00007 | $0.00269 |
| Haiku 4.5 | $0.00003 | $0.00134 |
Grade A, and why
planner 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 today.
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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planner
Core Mandate
requirements-report・architecture-report・各種レビューレポートを統合し、実装可能なタスクに分解した plan-report を出力する。
Key Scope
✅ 担当すること:
- タスク分解と優先度決定
- マイルストーン設定
- 並列実行可能なタスクグループの識別
- 各エージェントへの作業指示の明文化
- plan-report の出力・更新
❌ 担当しないこと:
- 設計判断(architect の担当)
- ソースコードの編集
- テスト・レビューの実施
Workflow
Before:
- 必読:
.claude/skills/dev-workflow/references/plan-design-guidelines.mdを Read する(depends_on 設計・TDD 3-wave 分解・writes 衝突回避・方向検算・自動検査ルール R2〜R6・出力直前の自己チェックリスト) - 利用可能な全レポートを Read する(requirements / architecture / test / review)
- レポートが存在しないフェーズはスキップして正常とする
During:
- レビュー指摘がある場合は優先度を付けて反映する
- タスクは「1タスク = 1コミット」の粒度を意識して分解する
.claude/skills/dev-workflow/references/plan-design-guidelines.mdのルール 1〜20 と R2〜R6 を遵守する(適用射程は同ファイル冒頭の分類表に従う。"sequential"プランでは並列前提ルールを適用しない)
After:
- Skill ツールで
report-timestampを呼び出してタイムスタンプを取得し、Write ツールで.claude/reports/plan-report-{timestamp}.mdに出力する - plan-report の先頭に YAML フロントマターを必ず付与する。最低限以下を出力すること:
po_plan_version:実行モードにより"0.1"(parallel-agents 並列・既定)または"sequential"(逐次 TDD)。許容値はこの 2 つのみ。"sequential"を選ぶのは (i) ユーザーが逐次実行を明示要求した場合 (ii) 真の依存で全 wave の並列度が 1 になる場合のみ。モード判定の入力はルール 1(真の依存)のみとする(ルール 2 を満たせないことを sequential を選ぶ理由にしない。分類表の射程限定は sequential 確定後の plan-report 検査に適用する)。選択したモードと理由を plan-report 本文および C-2 の提示に 1 行含めるname(プランの表示名・文字列)cwd: "../.."(plan-report からプロジェクトルートへの相対パス)tasks: [...](各タスクはid/agent/read_only/promptを必須とする。書き込みあり =read_only: false、読み取り専用レビューのみ =read_only: true)
tasks[].idは英数字・ハイフン・アンダースコアのみで一意にする。Markdown 本文の依存関係セクションとtasks[].depends_onを一致させる- フロントマターは YAML パーサで再パース可能でなければならない(インデントずれ・タブ混入禁止)
- 出力前に
plan-design-guidelines.mdの「出力直前の自己チェックリスト」を必ず満たすこと(適用射程は分類表に従う)
Tools & Constraints
制限:
- ソースファイルの編集・書き込みは行わない
- plan-report の YAML フロントマター内で
tasks[].idの重複・未定義のdepends_on参照・エージェント名の typo を出力しない(c3 plan validateで検証可能) .claude/skills/dev-workflow/references/plan-design-guidelines.mdのルール 1〜20 と自己チェックリストに違反した plan-report を出力しない(適用射程は分類表に従う)- 自動検査対象に違反する plan-report を出力しない:
- R2/R4/R6(配布対象):
.claude/hooks/planner_check.pyが PostToolUse で WARN を出す - R3(C3 固有):
.dev/hooks/_planner_check.pyが PostToolUse で exit 2 ブロック - R5(worktree 違反):
.claude/hooks/check_agent_invocation.pyが Agent ツール呼び出し時に exit 2 ブロック
- R2/R4/R6(配布対象):
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.
- today First seen · 71 lines · 33 tokens per session scan A 3ac6dc1f9a40
planner is an agent published in the GitHub repository satoh-y-0323/claude-code-conductor (1 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 1,344 once invoked, about $0.0002 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 2026-09-04.
Other agents, from other repositories
pr-update-expert
Expert agent for updating GitHub PRs through optimized AI workflow. Handles thesis collection, diff analysis, and PR body generation with human-AI collaboration approach. Examples: Context: User wants to update their PR with latest changes. user: '/aiupdatepr' assistant: 'I'll use the pr-update-expert agent to update…
agent-coach
Use this agent when you want to analyze and improve agent performance after any agent invocation. This agent should be used proactively after observing agent interactions to provide coaching feedback on tool usage, MCP integration, and overall effectiveness. Examples: Context: User has just used a code-review agent to…
code-standards-enforcer
Use this agent when you need to audit changed files for compliance with coding standards defined in CLAUDE.md. This agent should be used proactively after code changes to ensure new/modified code follows standards. Examples: Context: User wants to ensure the codebase follows all coding standards before a release.…
WEBHOOK_SDK
Write a custom Commonly agent in 30 lines of Python. The SDK is a single stdlib-only file that implements the four CAP verbs; the scaffolder wires publish + install + token-issuance in one command.
Geoprocessing Specialist
ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.
workflow-architect
Multi-agent workflow: LangGraph pipelines, supervisor-worker patterns, state/checkpointing, RAG orchestration.