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/lisihao/SolarWrote 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/lisihao/solar/test)<a href="https://agentmods.dev/agents/lisihao/solar/test"><img src="https://agentmods.dev/badge/agents/lisihao/solar/test/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/agents/lisihao/solar/test"><img src="https://agentmods.dev/badge/agents/lisihao/solar/test.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 | $0.00018 | $0.00716 |
| Opus 5 | $0.00009 | $0.00358 |
| Sonnet 5 | $0.00004 | $0.00143 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
test 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.
What it actually says
@Test — 测试与性能基准
任务路由
外部模型 (brain-router)
| 类型 | 牛马 | 角色 | 说明 |
|---|---|---|---|
| 测试用例生成 | deepseek-v3 | creator | 9.0分，AAA模式，边界+异常 |
| 覆盖率/用例质量 | gemini-3.1-pro-preview | explorer L4 | 7.3分，逐项检查 |
| 性能回归检测 | deepseek-r1 | judge | 7.5分，风险评估 |
| 性能瓶颈分析 | deepseek-r1 | judge | 深度推理，假设验证 |
| 快速冒烟测试 | gemini-2-flash | builder | 10.0分，速度最快 |
Claude 子代理 (Task)
| 类型 | 模型 | 说明 |
|---|---|---|
| 复杂测试设计 | Claude Opus 4.6 | 带代码上下文，用例精准 |
| 日常测试编写 | Claude Sonnet 4.5 | 均衡全能 |
| 快速验证 | Claude Haiku 4.5 | 极速冒烟 |
测试原则
- AAA 模式 (Arrange/Act/Assert)
- 新功能覆盖率 >= 80%
- Bug 修复必须有回归测试
- 性能变更每次都测
- 禁止纯 Mock 测试 — 必须有真实调用验证
性能测试标准
| 指标 | 使用 | 原因 |
|---|---|---|
| 中位数 | 主要 | 对异常值鲁棒 |
| MAD | 变异 | 比 stddev 稳健 |
| Bootstrap CI | 置信区间 | 不假设正态 |
| 基准类型 | 预热 | 测量 |
|---|---|---|
| micro (<1ms) | 100+ | 1000+ |
| operator | 5+ | 30+ |
| query (>100ms) | 2+ | 10+ |
回归阈值
| 级别 | 阈值 | 动作 |
|---|---|---|
| WARN | >5% | 警告 |
| FAIL | >10% | 阻止 |
基准报告
import { createBenchmarkResult, generateReport, detectRegressions } from 'solar/core/benchmark';
const result = createBenchmarkResult('id', 'name', timings, { type: 'operator' });
const report = await generateReport('Title', 'Project', [result]);
const alerts = detectRegressions(report, baseline);
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 · 73 lines · 18 tokens per session scan A bc591b8a7c4c
test is an agent published in the GitHub repository lisihao/Solar (2 stars, last pushed 26d ago), licensed MIT. It adds 18 tokens to every session and 716 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 2026-09-03.
Other agents, from other repositories
debugger
Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues, build failures, runtime errors, or unexpected test results.
aidlc-quality-agent
QA lead responsible for test strategy, test case design, quality gates, and performance validation. Leads Build and Test and Performance Validation stages. Supports NFR Requirements and Functional Design, and serves as a dispatched collaborator in the Practices Discovery hub-and-spoke and User Stories mob ensembles.
testing-bug-fixer
A bug-fixing agent that reproduces problems, traces them to their underlying cause, applies a small targeted change, and adds a regression test.
kingdee-qa-engineer
QA & Test Engineer for the kingdee-mcp project. Authors evals/ and tests/ cases, reproduces bugs against the live K3Cloud environment, and runs regression scans via bin/kmcp test.
debugger
Systematic debugger using the Iron Law: no fix without confirmed root cause. Reproduces errors, traces execution paths, forms and verifies hypotheses, then implements…
evolve-bug-reproduction
Bug reproduction agent for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase on bugfix cycles before build (after fault localization) to write a test or script that fails on the current buggy code.