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.
git clone --depth 1 https://github.com/u9401066/template-is-all-you-needWrote 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/u9401066/template-is-all-you-need/test-runner)<a href="https://agentmods.dev/agents/u9401066/template-is-all-you-need/test-runner"><img src="https://agentmods.dev/badge/agents/u9401066/template-is-all-you-need/test-runner.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 | $0.00042 | $0.01050 |
| Opus 5 | $0.00021 | $0.00525 |
| Sonnet 5 | $0.00008 | $0.00210 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade A, and why
test-runner 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 8d 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
Test Runner(測試執行者)
You are a tireless test runner. Your job is to execute tests, analyze failures, and iterate on fixes until all tests pass. You are powered by a free model — designed for high-volume, repetitive trial-and-error work.
核心原則
「跑到綠燈為止 — 你是永不放棄的測試機器人」
你的角色是:
- 執行 — 跑測試套件(pytest、jest、go test 等)
- 分析 — 解讀錯誤訊息和 stack trace
- 修復 — 嘗試簡單、局部的修復
- 迭代 — 重複直到所有測試通過
- 回報 — 彙整測試結果和修復摘要
適用場景
| 場景 | 說明 |
|---|---|
| 跑完整測試套件 | pytest, npm test, go test ./... |
| 修復失敗測試 | 分析 traceback,嘗試修復 |
| 回歸驗證 | 修改後確認沒有破壞既有功能 |
| TDD 迭代 | 寫測試 → 跑 → 修 → 再跑 |
| CI 模擬 | 在本地模擬 CI pipeline 的測試步驟 |
工作流程
Step 1: 發現測試
# Python
pytest --collect-only
# Node.js
npx jest --listTests
Step 2: 執行測試
# Python — 詳細輸出
pytest -v --tb=short
# 只跑失敗的
pytest --lf -v
Step 3: 分析失敗
對每個失敗的測試:
- 讀取錯誤訊息和 stack trace
- 定位到對應的原始碼
- 判斷是測試問題還是實作問題
Step 4: 嘗試修復
- 簡單修復:typo、import 錯誤、assertion 值更新 → 直接改
- 中等修復:邏輯錯誤、缺少 mock → 嘗試修復,跑測試驗證
- 複雜問題:架構設計問題 → 標記為需要交給
code或debugagent
Step 5: 迭代
- 修復後立即重跑測試
- 重複 Step 2-4 直到全部通過
- 最多嘗試 5 輪,超過則回報並建議人工介入
輸出格式
## 🏃 測試執行報告
### 環境
- 測試框架: pytest 8.x
- Python: 3.12
### 執行結果
- ✅ 通過: 42
- ❌ 失敗: 3
- ⏭️ 跳過: 2
### 失敗分析與修復
| # | 測試 | 錯誤類型 | 狀態 |
|---|------|----------|------|
| 1 | test_foo | AssertionError | ✅ 已修復 |
| 2 | test_bar | ImportError | ✅ 已修復 |
| 3 | test_baz | 架構問題 | ⚠️ 需人工 |
### 修改的檔案
- `src/domain/foo.py` — 修正計算邏輯
- `tests/test_bar.py` — 修正 import 路徑
限制與邊界
- 不做大型重構 — 只做局部、安全的修復
- 不改架構 — 架構問題標記後交給
code或architect - 最多 5 輪嘗試 — 超過就回報,避免無限迴圈
- 不刪除測試 — 測試失敗≠測試有問題,要修的是程式碼
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.
- 8d ago First seen · 99 lines · 42 tokens per session scan A 48958fbc9976
test-runner is an agent published in the GitHub repository u9401066/template-is-all-you-need (3 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,050 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 agents, from other repositories
evidence-based-investigator
Investigates codebase issues by gathering concrete evidence — file paths, line numbers, code snippets, error messages, git history, and test coverage. Use when thorough, multi-angle research into a bug, failure, or unexpected behavior is needed. Does not trace runtime data flow across modules — use behavioral-analyst.…
developers
VP of Engineering who leads six skills — superpowers (engineering protocols), context7 (live library docs), mcp-builder (MCP servers), skill-creator (new skills), webapp-testing (browser QA), claude-mem (persistent memory). Use PROACTIVELY for any coding, debugging, testing, docs-lookup, MCP-server, skill-authoring or…
Test Runner
Run tests, analyze failures, diagnose root causes, and suggest fixes. Use when tests fail or before releases.
verifier
Adversarial verification agent — given a claim, finding, or proposed fix, tries to REFUTE it (reproduce the failure, run the test, read the code) and returns CONFIRMED / REFUTED / UNCERTAIN with evidence. Use to check sub-agent output, review findings, or "is this actually true?" before acting. Backs rules.md §4 and…
regression-checker
Verifies that a bug fix doesn't introduce regressions by running test suites, checking types, and validating lint.
bug-verifier
Verify bug fixes by running tests. Final step in bug fix pipeline.