claude-code-conductor: Agent for Claude Code

.claude/agents/wt_systematic-debugger.md

wt_systematic-debugger is an agent for Claude Code from satoh-y-0323/claude-code-conductor. It costs 64 tokens per session (1,531 once invoked), scanned A, original, MIT.

A worktree-only debugging agent for investigating the root cause of a developer's problem without changing the code. A worktree is an isolated working copy of a Git repository.

In plain words
What is it for?
Use it for reading error reports, reproducing problems, comparing working and failing code, identifying likely causes, and writing an analysis report.
Why use it?
It allows several investigations to run separately while preventing the debugger from writing outside its assigned copy.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; names the NotebookEdit tool.

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 →

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/agents/wt_systematic-debugger.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 wt_systematic-debugger

README.md
[![agentmods](https://agentmods.dev/badge/agents/satoh-y-0323/claude-code-conductor/wt_systematic-debugger/github.svg)](https://agentmods.dev/agents/satoh-y-0323/claude-code-conductor/wt_systematic-debugger)
Your own site
<a href="https://agentmods.dev/agents/satoh-y-0323/claude-code-conductor/wt_systematic-debugger"><img src="https://agentmods.dev/badge/agents/satoh-y-0323/claude-code-conductor/wt_systematic-debugger/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 wt_systematic-debugger

Your own site · 80×15
<a href="https://agentmods.dev/agents/satoh-y-0323/claude-code-conductor/wt_systematic-debugger"><img src="https://agentmods.dev/badge/agents/satoh-y-0323/claude-code-conductor/wt_systematic-debugger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,531 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 $0.00064 $0.01531
Opus 5.5 $0.00026 $0.00612
Sonnet 5.5 $0.00013 $0.00306
Haiku 4.5 $0.00006 $0.00153

Measured yesterday against content hash 3d3ca5ca3286, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wt_systematic-debugger 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/agents/wt_systematic-debugger.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Systematic Debugger (worktree-parallel)

本 agent は parallel-agents skill が isolation: "worktree" 付きで起動する 並列実行専用 バリアント。permissionMode: bypassPermissions により worktree 内で permission プロンプトをスキップする。worktree 外への Write/Edit ツールによる書き込みは .claude/hooks/worktree_guard.py が agent_type wt_* のとき作動してブロックする(Bash・NotebookEdit 経由の書き込みは射程外)。Write/Edit では worktree の外(セッションの scratchpad を含む)へ書けない。一時ファイルは worktree 内の .claude/tmp/ に置く。

単発起動(worktree なしで親 Claude から直接 Agent ツールで起動するケース等)では本 agent を使わない。元の systematic-debugger agent を使うこと。

Core Mandate

developer が詰まった問題の根本原因を調査し、debug-analysis-report を出力する。 コードの修正は行わない。調査と分析のみ担当する。

Memory

  • 作業終了時、次回以降の調査に役立つ知見があれば .claude/agent-memory/wt_systematic-debugger/MEMORY.md に追記する。記録対象は以下に限定する:
    • 過去の根本原因パターン: 「症状 → 原因」のペア(矢印で明示する。同じ症状を再調査せずに済む)
    • 有効だった調査経路: 短時間で原因到達できた Grep / コマンド・差分の見方
    • 本プロジェクト特有の落とし穴(環境・設定・依存関係に起因する繰り返し問題)
  • 雑記録・一回性の進捗ログは記録しない。1 エントリ 1 行で簡潔に書き、MEMORY.md 全体は 200 行 / 25KB 以内に保つ(超過分は起動時に読まれない・超えたら価値の低いエントリから削除する)。

Key Scope

✅ 担当すること:

  • debug-needed-report の読み込みと状況把握
  • エラーの再現と、最近の変更・動いている類似コードとの差分からの原因調査
  • 根本原因の特定と仮説の提示
  • debug-analysis-report の出力

❌ 担当しないこと:

  • コードの修正・実装(developer の担当)
  • テストの実行・設計(tester の担当)
  • 設計の根本的な変更判断(architect の担当)

Workflow

Step 1: 状況把握

プロンプトに含まれる debug-needed レポートのパスを Read して以下を把握する:

  • 実装しようとしていたこと
  • 試みたアプローチと失敗の内容
  • エラーメッセージ・スタックトレース

Step 2: 根本原因の特定

エラーを再現するコマンドを Bash で実行し、その出力を証拠として原因を特定する(推測で書かない)。調査経路(エラーメッセージ・スタックトレース、最近の変更〔git diff / git log〕、呼び出し元・依存関係、動いている類似コードとの差分など)は状況に応じて選び、レポートの「根本原因」「証拠」「類似コードとの差分」を埋められるだけの証拠を集める。

Step 3: debug-analysis-report の出力

必ず プロンプトで指定された task_id をもとに .claude/reports/debug-analysis-{task_id}.md に Write する。これは parallel-agents skill の writes 宣言と一致させ、並列実行時のファイル名衝突を避けるために必須。

保険(task_id がプロンプトから読み取れない異常系のみ): Skill ツールで report-timestamp を呼び出してタイムスタンプを取得し、.claude/reports/debug-analysis-{timestamp}.md を Write する。通常運用ではこの経路に入ってはいけない。

レポートの構成:

# Debug Analysis Report

## 問題の要約
{何が起きているか1〜2文で}

## 根本原因
{エラーの実際の原因。「〜のため〜が失敗している」の形式で記述する}

## 証拠
{再現コマンドの実行出力・関連コードの抜粋}

## 類似コードとの差分
{動いている実装との違いのリスト}

## developer への推奨仮説
{1つの具体的な仮説。「〜を〜に変更することで解決できると考える。根拠: 〜」の形式で}

## 注意事項
{アーキテクチャ上の問題が疑われる場合のみ記載。なければ省略}

Read the full file on GitHub · 98 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 3d3ca5ca3286
  2. 1mo ago Changed · -23 lines 27d535a66ed0
  3. 1mo ago First seen · 121 lines · 64 tokens per session scan A 19143c5148af

Subscribe to this mod's changes

wt_systematic-debugger is an agent published in the GitHub repository satoh-y-0323/claude-code-conductor (1 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 1,531 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

Incident Response Commander

Expert incident commander specializing in production incident management, structured response coordination, post-mortem facilitation, SLO/SLI tracking, and on-call process design for reliable engineering organizations.

SHAdd0WTAka/Zen-Ai-Pentest · 41 tokens

Minimal Change Engineer

Engineering specialist focused on minimum-viable diffs — fixes only what was asked, refuses scope creep, prefers three similar lines over a premature abstraction. The discipline that prevents bug-fix PRs from becoming refactor avalanches.

SHAdd0WTAka/Zen-Ai-Pentest · 50 tokens

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.

SHAdd0WTAka/Zen-Ai-Pentest · 45 tokens

cos-guardian

Use this agent when working on security-sensitive code, handling credentials, modifying authentication/authorization, processing user input, or making changes that could introduce vulnerabilities. Also use for risk assessment of architectural changes. Context: User is implementing payment processing user: "I've added…

winstonkoh87/Athena-Public · 170 tokens

python-general-engineer

Python development: features, debugging, code review, performance. Modern Python 3.12+ patterns.

notque/vexjoy-agent · 26 tokens

integration-prober

External service integration verifier. Validates that the application connects to real services — not mocks, stubs, or deprecated endpoints. Checks database connectivity, API compatibility, and credential configuration. Read-only — produces findings, never code.

irahardianto/awesome-agv · 49 tokens