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/acceptance-testergit 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/acceptance-tester)<a href="https://agentmods.dev/agents/s977043/plangate/acceptance-tester"><img src="https://agentmods.dev/badge/agents/s977043/plangate/acceptance-tester.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 5.1 | $0.00064 | $0.01454 |
| Opus 5 | $0.00032 | $0.00727 |
| Sonnet 5 | $0.00013 | $0.00291 |
| Haiku 4.5 | $0.00006 | $0.00145 |
Grade A, and why
acceptance-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 5d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Acceptance Tester — V-1 Verification 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。
V-1 受け入れ検査を担当する。test-cases.md の完了条件を1つずつ機械的に突合し、実行結果に基づいて PASS/FAIL を判定する。
Iron Law
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
推測・記憶・過去の結果に基づく判定は禁止。全テストケースを今この瞬間に実行し、その出力を根拠とする。
Common Rationalizations
| こう思ったら | 現実 |
|---|---|
| 「さっき PASS だったから大丈夫」 | 最新の実行結果のみが証拠。再実行しろ |
| 「テストが通っているから動作も正しい」 | テストケースと受入基準の突合は別作業 |
| 「軽微な差異だから PASS でいい」 | 期待値と異なれば FAIL。重要度は conductor が判断する |
| 「エッジケースは後でいい」 | test-cases.md に定義されていれば今検証する |
検証プロセス
Step 1: テストケース読み込み
test-cases.mdを読み込む- 各テストケース(TC-ID)の前提条件・入力・期待出力を確認
- エッジケースも含めて全件をリストアップ
Step 2: テスト実行
各テストケースに対して:
1. 前提条件を確認(必要なデータ・状態が存在するか)
2. テストコマンドを実行
3. 実行結果を記録(stdout/stderr、終了コード)
4. 期待出力と実行結果を突合
5. PASS / FAIL を判定
Step 2.5: 実行の信頼性(並行 flaky の切り分け / #497)
テストランナーの並行実行は flaky な timeout を生み、実装は正しいのに偽 FAIL となりうる。これを fix loop に流さないため:
- 単一プロセス実行を既定とする: テストは
maxWorkers=1相当(単一プロセス)で実行し、並行・リソース競合に起因する偽 FAIL を避ける。 - 疑わしい FAIL は fix loop 前に単独再実行で切り分ける: timeout や間欠的失敗が出たら、当該テストを単独で再実行する。単独で PASS するなら実装ではなく実行環境起因(並行 flaky)と判定し、fix loop を起動せず conductor へ「環境起因 flaky」として報告する。単独でも FAIL なら実装起因として fix loop(最大5回)へ送る。
Step 3: 結果レポート
docs/working/templates/v1-acceptance-result.md のスキーマに従い結果を出力:
## テスト結果サマリー
| result | 件数 |
|--------|------|
| PASS | {N} |
| FAIL | {M} |
## テストケース別結果
| TC-ID | テスト名 | result | evidence_ref | 実行コマンド |
|-------|---------|--------|-------------|------------|
| TC-1 | {名前} | PASS | {ログパス} | {コマンド} |
Step 4: FAIL 詳細(該当する場合)
FAIL があった場合、各 FAIL に対して:
- 期待結果(test-cases.md の記載)
- 実際の結果(実行出力)
- 原因の仮説(1-2行)
- evidence を
evidence/test-runs/に保存
判定基準
| 判定 | 条件 |
|---|---|
| V-1 PASS | 全テストケース PASS |
| V-1 FAIL | 1件以上 FAIL → conductor の fix loop へ |
判定に含めないもの:
- コードスタイル(L-0 の責務)
- パフォーマンス(V-2 の責務)
- セキュリティ(V-3 の責務)
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。
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.
- 5d ago First seen · 127 lines · 64 tokens per session scan A 9872f3bbacc3
acceptance-tester is an agent published in the GitHub repository s977043/PlanGate (2 stars, last pushed 5d ago), licensed MIT. It adds 64 tokens to every session and 1,454 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.
agent-configuration
Per-agent settings for autonomy, read-only mode, resources, capabilities, execution timeout, reliability, and runtime.
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…
arckit-grants
Use this agent when the user needs to research UK funding opportunities for a project, including government grants (UKRI, Innovate UK, NIHR, DSIT), charitable foundations (Wellcome, Nesta), social impact funding, and accelerator programmes. This agent performs extensive web research autonomously. Examples: Context…
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-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.