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 skills add morodomi/tdd-skills --skill tdd-orchestrategit clone --depth 1 https://github.com/morodomi/tdd-skillsWrote 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/skills/morodomi/tdd-skills/tdd-orchestrate)<a href="https://agentmods.dev/skills/morodomi/tdd-skills/tdd-orchestrate"><img src="https://agentmods.dev/badge/skills/morodomi/tdd-skills/tdd-orchestrate/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.
<a href="https://agentmods.dev/skills/morodomi/tdd-skills/tdd-orchestrate"><img src="https://agentmods.dev/badge/skills/morodomi/tdd-skills/tdd-orchestrate.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00047 | $0.00796 |
| Opus 5 | $0.00023 | $0.00398 |
| Sonnet 5 | $0.00009 | $0.00159 |
| Haiku 4.5 | $0.00005 | $0.00080 |
Grade A, and why
tdd-orchestrate 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 12d 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.
What it actually says
TDD Orchestrate (PdM Mode)
TDDサイクル全体をPdM (Product Manager) として管理するオーケストレータ。
Progress Checklist
tdd-orchestrate Progress:
- [ ] Block 1: INIT → PLAN → plan-review → 自律判断
- [ ] Block 2: RED → GREEN → REFACTOR → REVIEW → 自律判断 → DISCOVERED
- [ ] Block 3: COMMIT → 完了
PdM の原則
- 自分で実装・テスト・レビューしない → 専門 Teammate/Subagent に委譲
- PASS/WARN → 自動進行、BLOCK → 再試行 → ユーザーに報告
- 曖昧なまま進まない → AskUserQuestion で確認
Workflow
Block 1: Planning
- INIT: Cycle doc 作成（PdM 直接実行）
- PLAN: 設計・Test List 作成を委譲
- plan-review: 5 reviewer で設計レビュー
- 自律判断: PASS/WARN → Block 2 へ、BLOCK → PLAN 再実行
Block 2: Implementation
- RED: red-worker にテスト作成を委譲
- GREEN: green-worker に実装を委譲
- REFACTOR: refactorer にリファクタリングを委譲
- REVIEW: quality-gate で 6 reviewer レビュー
- 自律判断: PASS/WARN → DISCOVERED 判断 → Block 3 へ、BLOCK → GREEN 再実行
- DISCOVERED: スコープ外項目を GitHub issue に起票（ユーザー確認後）
Block 3: Finalization
- COMMIT: git add & commit（PdM 直接実行）
- 完了報告: サイクル完了をユーザーに報告
Mode Selection
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS 環境変数でモードを選択:
| 環境変数 | モード | 手順 |
|---|---|---|
有効 (1) |
Agent Teams (PdM Hub) | steps-teams.md |
| 無効 / 未設定 | Subagent Chain | steps-subagent.md |
Judgment Criteria
| スコア | 判定 | PdM アクション |
|---|---|---|
| 0-49 | PASS | 次 Block へ自動進行 |
| 50-79 | WARN | Socrates Protocol → 人間判断 (Agent Teams時) |
| 80-100 | BLOCK | Socrates Protocol → 人間判断 (Agent Teams時) |
Agent Teams 無効時は WARN 自動進行、BLOCK 自動再試行 (v5.0 互換)。 Socrates Protocol 詳細: reference.md
Reference
- PdM 責務・判断基準: reference.md
- Agent Teams 手順: steps-teams.md
- Subagent 手順: steps-subagent.md
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 73 lines · 47 tokens per session scan A a517881cd573
tdd-orchestrate is a skill published in the GitHub repository morodomi/tdd-skills (8 stars, last pushed 7mo ago), licensed MIT. It adds 47 tokens to every session and 796 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 2026-08-31.
Other skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
python
Python development with ruff, mypy, pytest - TDD and type safety.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.