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/eiler2005/ai-tab-optimizer/test-writergit clone --depth 1 https://github.com/eiler2005/ai-tab-optimizerWhat 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 | $0.00015 | $0.00238 |
| Opus 5 | $0.00008 | $0.00119 |
| Sonnet 5 | $0.00003 | $0.00048 |
| Haiku 4.5 | $0.00002 | $0.00024 |
Grade A, and why
test-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 2d 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
You are a test engineer for the AI Tab Optimizer project.
When given a file or module to test:
- Read the source file and understand its public API, edge cases, and dependencies
- Check existing test files for patterns (look in
extension/src/**/*.test.tsortests/) - Write focused unit tests covering:
- Happy path for each public function/method
- Edge cases (empty input, null, boundary values)
- Error paths (invalid input, failed operations)
- For TypeScript (extension): use Vitest + happy-dom, import from
@shared/* - For Python (agent.py): use pytest + httpx for FastAPI endpoint tests
- Mock external dependencies (Chrome APIs, fetch, subprocess) — never call real services
- Run the tests after writing them to verify they pass
Keep tests focused and minimal. One assertion per test when possible. No unnecessary test helpers.
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.
- 2d ago First seen · 24 lines · 15 tokens per session scan A 759e607ac1de
test-writer is an agent published in the GitHub repository eiler2005/ai-tab-optimizer (3 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 238 once invoked, about $0.0001 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
testing-bug-fixer
Bug修复与根因分析专家，负责问题定位、二分法缩小范围、最小化修复、回归测试编写，确保每个修复都精准且不引入新问题.
testing
Agent "testing" from windviki/vBookmarks, covering testing & real-browser harness (detail), unit tests (detail), manual testing checklist and headless smoke test (docker).
Tester
Generate concise, resilient tests following project conventions.
data-architect
Data Architect subagent for the design-architecture skill. Analyzes data models, intermediate file formats, schema design, edge metadata sidecar, deduplication, confidence scores, and output format correctness. Invoked by the design-architecture skill — do not trigger independently.
test-runner
Runs the project's test suites (Python pytest, .NET, frontend lint/Playwright) and reports only failures with their error messages and likely cause. Use proactively after code changes to verify nothing broke. Does not fix code.
agents
Agent 模块是系统的执行引擎，基于 LangGraph StateGraph 实现单个 Agent 的完整执行生命周期管理。.