agentmods.dev

claude-code-conductor: Skill for Claude Code

.claude/skills/parallel-agents/SKILL.md

parallel-agents is a skill for Claude Code from satoh-y-0323/claude-code-conductor. It costs 44 tokens per session (11,343 once invoked), scanned A, original, MIT.

A procedure for running independent development tasks at the same time in separate Git worktrees, which are isolated working copies of a repository. A parent agent combines the completed work after each group of tasks finishes.

In plain words
What is it for?
Use it in development plans that divide work into parallel tasks, especially when each task can be completed safely in its own worktree.
Why use it?
It lets unrelated tasks proceed concurrently while keeping their file changes separated. It also defines how task groups are ordered and how the results are brought back together.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is satoh-y-0323/claude-code-conductor's own configuration. It tells Claude Code how to work on claude-code-conductor itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-code-conductor configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is summary_file = '../tmp/wave-checkpoint-summary.txt'.

not rated 1repo changed yesterday A scan 44 tokens original MIT
View source ↗ satoh-y-0323/claude-code-conductor
Reuse

Borrowing it

Nothing to install: this file belongs to satoh-y-0323/claude-code-conductor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/satoh-y-0323/claude-code-conductor/main/.claude/skills/parallel-agents/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/satoh-y-0323/claude-code-conductor

Made for: Claude Code.

Wrote 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.

agentmods badge for parallel-agents

README.md
[![agentmods](https://agentmods.dev/badge/skills/satoh-y-0323/claude-code-conductor/parallel-agents/github.svg)](https://agentmods.dev/skills/satoh-y-0323/claude-code-conductor/parallel-agents)
Your own site
<a href="https://agentmods.dev/skills/satoh-y-0323/claude-code-conductor/parallel-agents"><img src="https://agentmods.dev/badge/skills/satoh-y-0323/claude-code-conductor/parallel-agents/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for parallel-agents

Your own site · 80×15
<a href="https://agentmods.dev/skills/satoh-y-0323/claude-code-conductor/parallel-agents"><img src="https://agentmods.dev/badge/skills/satoh-y-0323/claude-code-conductor/parallel-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11,343 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00044 $0.11343
Opus 5.5 $0.00018 $0.04537
Sonnet 5.5 $0.00009 $0.02269
Haiku 4.5 $0.00004 $0.01134

Measured yesterday against content hash 40fc99823514, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

parallel-agents 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 yesterday.

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.

.claude/skills/parallel-agents/SKILL.md · 419 lines

How it starts

The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Parallel Agents

/develop のフェーズ D で plan-report に YAML フロントマター内の po_plan_version 値が "0.1" のときに Read される手順（"sequential" または フロントマター無しのプランは dev-workflow の legacy TDD 経路へ振り分けられる）。

C3 の親 Claude が plan-report の DAG を wave 単位 で歩く:

  1. 各 wave 内のタスクを 1 ターン内で複数 Agent ツール並列起動
  2. 各 Agent は isolation: "worktree" 付きで独立した git worktree 内で完結
  3. 親 Claude が wave 完了後に各 worktree の成果物を取り込み、一括コミット

並列実行は Claude Code 公式の isolation: "worktree" フロントマターに依拠する。

depth 1 制限について

Claude Code のサブエージェントは 更にサブエージェントを spawn できない（公式仕様 depth 1 制限）。配布 agent はいずれも内部で Agent ツールを使わない設計のため、すべて並列起動可能。

将来的に「内部で Agent ツールを使う agent」を追加する場合は、その agent を含む wave のタスク数を 1 に絞る運用ガードが必要になる。

subagent_type 明示指定と wt_* 名前空間

subagent_type パラメータには カスタム agent (.claude/agents/*.md) も指定可能（公式仕様）。これにより frontmatter の permissionMode / tools / model / memory が subagent 起動レイヤーで自動適用される。

並列実行で permission プロンプトに詰まらないよう、worktree 専用の wt_* プレフィックス agent を使う:

  • wt_tester / wt_developer / wt_systematic-debugger: frontmatter に permissionMode: bypassPermissions を持つ並列専用バリアント
  • 本体ロジックはオリジナルの tester / developer / systematic-debugger と同等。差分はレポート出力のファイル名規約のみで、並列専用 agent は test-report-{task_id}.md / debug-needed-{task_id}.md / debug-analysis-{task_id}.md を主経路とする（タイムスタンプ形式は task_id 不在時の保険）
  • worktree 内のみで動作するため、.claude/hooks/worktree_guard.py (PreToolUse) が worktree 外への Write/Edit ツールによる書き込みをブロックする保護下にある（Bash・NotebookEdit 経由の書き込みは射程外）。作動条件は hook 入力の agent_type で、wt_developer / wt_tester / wt_systematic-debugger のとき自動で作動する（env の設定は不要）。worktree の外（セッションの scratchpad を含む）へは書けない。緊急無効化は C3_WORKTREE_GUARD_DISABLE=1

直接起動経路（worktree なし）では元の agent を使い、main リポジトリでの bypass を防ぐ。

前提条件

  • plan-report が .claude/reports/plan-report-*.md の形式で配置され、YAML フロントマターを持つこと（po_plan_version: "0.1"）
  • po_plan_version: "sequential" またはフロントマター無しの plan-report は D-0 が legacy 逐次 TDD（D-1〜D-5）へ振り分ける（本 skill には入らない）
  • Claude Code の Agent ツールが isolation: "worktree" パラメータをサポートしていること（v2.1.x 以降。利用者向け推奨設定は .claude/docs/parallel-agents-setup.md を参照）

Read the full file on GitHub · 419 lines

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. yesterday Changed · -4 lines 40fc99823514
  2. 1mo ago Changed · +2 lines · -8 tokens per session 5682f6b40607
  3. 1mo ago First seen · 421 lines · 52 tokens per session scan A 4dd37d8cd42d

Subscribe to this mod's changes

parallel-agents is a skill published in the GitHub repository satoh-y-0323/claude-code-conductor (1 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 11,343 once invoked, about $0.0002 per session on Opus 5.5. 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.

Building agentsClaude CodeGit and workflowMulti-AgentPythonframeworkworkflow
Related

Other skills, from other repositories

git-worktree-swarm

Automates the complex setup of parallel git worktrees for agentic swarms with dependency-aware wave execution.

winstonkoh87/Athena-Public · 27 tokens

git-workflow

Git operations: commits, branches, PRs, and conflict resolution.

vstorm-co/pydantic-deepagents · 17 tokens

Release Notes Generator

Generate professional software release notes from a commit log: classify changes, write user-facing summaries, draft a publishable announcement, and assess release readiness. Use for release, changelog, version, and deploy requests.

AgentEra/Agently · 46 tokens

pinned-release-checklist

Minimal guidance-only Skill used by release-pinned compatibility examples.

AgentEra/Agently · 18 tokens

Release Checklist

Check release readiness and record a release note. Use for release and rollback requests.

AgentEra/Agently · 19 tokens

Release Readiness Reviewer

Reviews a release candidate and produces a go/no-go readiness decision.

AgentEra/Agently · 18 tokens