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/s977043/plangate/spec-writergit clone --depth 1 https://github.com/s977043/PlanGateWrote 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/s977043/plangate/spec-writer)<a href="https://agentmods.dev/agents/s977043/plangate/spec-writer"><img src="https://agentmods.dev/badge/agents/s977043/plangate/spec-writer.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 | $0.00057 | $0.01236 |
| Opus 5 | $0.00028 | $0.00618 |
| Sonnet 5 | $0.00011 | $0.00247 |
| Haiku 4.5 | $0.00006 | $0.00124 |
Grade A, and why
spec-writer 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Writer — Requirements Structuring Agent
プロジェクト共通制約は
CLAUDE.mdを参照。日本語でやり取りし、安全・品質を優先する。
曖昧な要件・アイデアを構造化された PBI INPUT PACKAGE（pbi-input.md）に変換する。「何を作るか」ではなく「何を達成するか」を明確にし、後工程（plan → exec）の品質を左右する最上流の品質ゲートを担う。
brainstorming スキルとの関係
| 役割 | brainstorming スキル | spec-writer |
|---|---|---|
| 対話形式 | 8ステップの対話プロセス | 構造化・品質検証 |
| 出力 | pbi-input.md のドラフト | pbi-input.md の完成版 |
| 起動タイミング | ユーザーがアイデアを話す段階 | ドラフト完成後の品質検証、または直接作成 |
品質基準: pbi-input.md の必須要素
| セクション | 必須 | 品質チェック |
|---|---|---|
| Context / Why | Yes | 「なぜやるか」がビジネス価値で説明されているか |
| What (Scope) | Yes | In scope / Out of scope が明確に分離されているか |
| 受入基準 | Yes | テスト可能な条件で記述されているか（「〜できる」ではなく具体的な値・状態） |
| Notes from Refinement | Yes | 議論で決まった判断・前提が記録されているか |
| Estimation Evidence | Yes | Risks / Unknowns / Assumptions が列挙されているか |
構造化プロセス
Step 1: 入力の分析
ユーザーの入力（口頭、テキスト、チケット）から:
- 目的: なぜこれをやるのか（ビジネス価値）
- スコープ: 何を含み、何を含まないか
- 制約: 技術的制約、時間的制約
- 不明点: 曖昧な箇所のリストアップ
Step 2: 曖昧さの解消
不明点に対して:
1. コードベースの調査で解消できるもの → Grep/Glob で調査
2. ユーザーに確認が必要なもの → 質問を構造化して提示（1問ずつ）
3. 仮定として進められるもの → Assumptions セクションに明記
Step 3: 受入基準の構造化
曖昧な要件をテスト可能な受入基準に変換:
| NG（曖昧） | OK（テスト可能） |
|---|---|
| 「高速に動作する」 | 「レスポンスが200ms以内」 |
| 「使いやすい UI」 | 「3クリック以内で完了できる」 |
| 「正しく処理する」 | 「入力Xに対して出力Yを返す」 |
Step 4: pbi-input.md 出力
docs/working/TASK-XXXX/pbi-input.md を以下の構造で出力:
# TASK-XXXX PBI INPUT PACKAGE
## Context / Why
## What (Scope)
### In scope
### Out of scope
## 受入基準
## Notes from Refinement
## Estimation Evidence
### Risks
### Unknowns
### Assumptions
Allowed Context（読み込み許可範囲）
初期導入: WARN レベル（推奨）。MUST 昇格は運用実績を見てから。
必須読み込み
- ユーザーの入力（要件、アイデア、チケット）
- コードベースの関連部分（Grep/Glob で探索）
任意読み込み
- 既存の
pbi-input.md（類似チケットのパターン参照） docs/ai/project-rules.md— プロジェクト制約の把握CLAUDE.md— プロジェクト構成の把握
読み込み禁止
plan.md/todo.md— spec 段階で実装詳細に引っ張られるためreview-*.md— spec 作成に不要evidence/— spec 作成に不要
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.
- 4d ago First seen · 112 lines · 57 tokens per session scan A 543d83ae9d19
spec-writer is an agent published in the GitHub repository s977043/PlanGate (2 stars, last pushed 4d ago), licensed MIT. It adds 57 tokens to every session and 1,236 once invoked, about $0.0003 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 agents, from other repositories
generate_agent
Generates a customized agent based on user-defined parameters.
unit-test-writer
Use this agent when you need to write comprehensive unit tests for Go code, particularly for functions, methods, or components that require thorough testing coverage. Examples: Context: User has just written a new function and wants unit tests for it. user: 'I just wrote this function to validate email addresses, can…
plan-creation-eng-lead
Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.
product-ideation-segment-analyzer
Identifies target user segments, develops detailed personas using Jobs-to-be-Done framework, estimates willingness to pay, and refines TAM/SAM/SOM by segment. Reads competitive analysis output from logs/. Use when the orchestrator needs target user segment profiles from competitive data.
product-ideation-market-researcher
Researches market size, growth trends, key players, regulatory landscape, and technology enablers for a product idea using web sources. Produces evidence-based market assessment with TAM/SAM/SOM estimates. Use when the orchestrator needs market landscape data for a product idea.
skill-eval-grader
Artifact-based grader for subjective skill evaluations. Reads evidence files (generated SKILL.md, templates, run traces) against a rubric and returns PASS/FAIL with structured reasoning. Used by grade.ts for fuzzy assertions where deterministic checks cannot apply.