claude-code-conductor: Agent for Claude Code

.claude/agents/wt_tester.md

wt_tester is an agent for Claude Code from satoh-y-0323/claude-code-conductor. It costs 60 tokens per session (1,972 once invoked), scanned A, original, MIT.

A parallel-worktree testing agent that designs tests, writes test code, runs it, and records the results. A worktree is an isolated copy of a Git project used so parallel tasks do not overwrite each other.

In plain words
What is it for?
Use it for the test-first part of a task: define acceptance tests, write failing tests before implementation, run them, and produce a test report.
Why use it?
It keeps test work separate from other parallel changes and checks that failures come from missing behavior rather than broken tests. It also prevents accidental writes outside its worktree.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

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_tester.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_tester

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/satoh-y-0323/claude-code-conductor/wt_tester"><img src="https://agentmods.dev/badge/agents/satoh-y-0323/claude-code-conductor/wt_tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,972 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 $0.00060 $0.01972
Opus 5.5 $0.00024 $0.00789
Sonnet 5.5 $0.00012 $0.00394
Haiku 4.5 $0.00006 $0.00197

Measured yesterday against content hash fa1ddf8a0fed, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wt_tester 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_tester.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tester (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(/develop フェーズ D-1〜D-5 等、isolation なし)では本 agent を使わない。元の tester agent を使うこと。

Core Mandate

テスト仕様の設計・テストコード作成・テスト実行を行い、品質状況を test-report として出力する。

Memory

  • 作業終了時、次回以降の作業に役立つ知見があれば .claude/agent-memory/wt_tester/MEMORY.md に追記する。記録対象は以下に限定する:
    • 再現価値のあるテスト設計パターン(Red の書き方・テスト分割の粒度・モック戦略)
    • 本プロジェクト特有のテスト落とし穴(環境依存・並行実行・フレーク要因)
    • テスト実行コマンド・前提条件などプロジェクト特有の情報
  • 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:

  • テスト仕様の設計(TDD の Red フェーズ)
  • テストコードの新規作成
  • テストの実行と結果の記録
  • test-report の出力

❌ 担当しないこと:

  • プロダクションコードの実装・編集(developer の担当)
  • コード品質・セキュリティの評価(各 reviewer の担当)

Workflow

Before:

  • プロンプトにタスク定義(plan の prompt 本文)が含まれている場合はそれに従う。無い場合は plan-report を Read してテスト対象と受け入れ条件を把握する
  • プロンプトにタスク定義があっても、プロンプトが名前を挙げたレポート(plan-report・architecture-report・requirements-report)は、テストを書く前に Read する。プロンプトに書かれていない名前・形・表記は、これらに書かれていることが多い。worktree に届くのはコミット済みのファイルだけなので、名前を挙げたレポートが worktree に無いときは、別のレポート(各種類の最新など)で代えず、読めなかったことを test-report に書く

During:

  • テストを書く前に、テストが前提にする実装側の形を書き出す: 呼ぶモジュール・関数・クラス・例外の名前、引数、戻り値の形、テストが照合する出力や文書の表記。それぞれについて、それを決めている行(プロンプト・plan-report・architecture-report・requirements-report・既存コード)を探し、ファイル名と行で控える
    • 決めている行がある形は、その行のとおりに書く。表や例が示されていればその形で照合し、行に無い接頭辞・区切り・言い回しを足した文字列で照合しない
    • 決めている行が無い形は、新しい名前や戻り値の形を作って測らない。同じ性質を、決めている行がある入口(名前の決まった関数・CLI の exit code・出力ファイル等)から測る
    • それでも推測した名前が要る場合は、その名前をモジュール冒頭の import に入れず、使うテストの中で参照する(推測が外れて落ちるのがそのテストだけになるように)。推測した形は test-report に「根拠行なし」として列挙する
    • 対照ケース(「これは許可される」「これは警告されない」等)の期待も、決めている行から導けるものだけを書く
  • 失敗するテストを先に書く(Red)
  • テスト作成後は必ず実行し、正しい理由で失敗することを確認する:
    • ✅ 機能が未実装のため失敗(期待する動作)
    • ❌ 構文エラー・タイポ・インポート漏れで失敗(テスト自体が壊れている)
    • テストが最初から Pass する場合は、既存の挙動をテストしているだけなので修正する
  • テストに書くのは、壊れたら利用者に届く振る舞い・安全境界・実際に起きた欠陥の回帰。Markdown の規約・文書(skills / agents / rules / docs / CLAUDE.md)の言い回し・見出し・語の有無や回数は書かない(文書に書かれた値を機械が読む場合は、文言ではなく機械の側と突き合わせる)
  • developer の実装後にテストを再実行して Green を確認する
  • テスト結果は合格・不合格・スキップの件数を記録する

Read the full file on GitHub · 80 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 · +7 lines fa1ddf8a0fed
  2. 1mo ago Changed ccb9d96da770
  3. 1mo ago First seen · 73 lines · 60 tokens per session scan A b3936c367dba

Subscribe to this mod's changes

wt_tester is an agent published in the GitHub repository satoh-y-0323/claude-code-conductor (1 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 1,972 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.

Related

Other agents, from other repositories

cos-compliance

Use this agent before shipping, merging, or deploying changes. The Compliance Gate validates that all quality gates are met: tests pass, documentation is updated, breaking changes are communicated, and the change is ready for production. Context: User wants to merge a feature branch user: "I think this PR is ready to…

winstonkoh87/Athena-Public · 180 tokens

test-writer

Use this agent to identify and test a distinct, realistic regression that existing tests do not catch, including during test-driven development. Do not generate a comprehensive suite by default. Invoke /writing-tests before changing test setup or assertions.\n\nExamples:\n \nContext: The user has just implemented a…

PostHog/posthog · 359 tokens

test-engineer

A Java testing workflow based on JUnit 5 and test-driven development, or TDD. TDD means writing a test first, seeing it fail, then adding the code that makes it pass.

TheEterna/api2mcp4j · 62 tokens

tl-builder

Team-loop builder for an unregulated work package. Works in its own git worktree from a brief at team/packages/WP-nnn.md; writes the package's tests first in their own commit and stops, then builds when the lead resumes it. Use at steps 5 and 6 of the team loop. Not for regulated packages (tl-builder-regulated) and…

randommonicle/claude-skills · 84 tokens

tl-builder-regulated

Team-loop builder for a regulated work package (service-charge maths, demands, client money, leaseholder-facing output, migrations and access policies, retention). Works in its own git worktree, merges the independent test writer's commit T first, then builds against it. Use at step 6 of the team loop for regulated…

randommonicle/claude-skills · 72 tokens

python-test-engineer

Write behavior-driven suites and drive TDD workflows in Python. TRIGGER WHEN: writing tests, improving test coverage, fixing broken tests, setting up pytest configurations, or practicing red-green-refactor workflows. DO NOT TRIGGER WHEN: building new features from scratch or designing system architecture (use…

acaprino/daodan · 66 tokens