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 commands/echovic/boss-skill/boss-qagit clone --depth 1 https://github.com/echoVic/boss-skillWrote 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/commands/echovic/boss-skill/boss-qa)<a href="https://agentmods.dev/commands/echovic/boss-skill/boss-qa"><img src="https://agentmods.dev/badge/commands/echovic/boss-skill/boss-qa.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 | $0.00049 | $0.00636 |
| Opus 5 | $0.00024 | $0.00318 |
| Sonnet 5 | $0.00010 | $0.00127 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
boss:qa 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.
What it actually says
/boss:qa — 单环节：测试与门禁（QA）
/boss:qa 是 Boss 流水线的测试环节独立入口。以 QA 身份对已有代码执行核心用户路径测试、真实 payload 验证、越权/分页/旧数据检查，产出 qa-report.md，并运行质量门禁。
与 gstack
/qa的关键区别：Boss 的门禁不可绕过且可验证——测试是否真跑、门禁是否真过，都进事件流（有 CLI 时）或写入 STATE.md（无 CLI 时），不是 agent 自报「测过了」。
适合 / 不适合
适合 /boss:qa |
不适合 |
|---|---|
| 对已实现功能补测试证据 | 还没有可测代码（先 /boss 开发） |
| 上线前跑门禁 checklist | 只想看代码不想跑测试 |
| 验证「测试真的跑过了」 | — |
执行步骤
- 读取
SKILL.md不变量与references/testing-standards.md、references/quality-gate.md。 - 确定被测目标（feature slug 或代码路径）。
- 读取
agents/boss-qa.md与skills/qa/test-strategy/SKILL.md、skills/qa/test-execution/SKILL.md、skills/qa/e2e-playwright/SKILL.md。 - 以 QA 身份执行测试并产出
qa-report.md（模板templates/qa-report.md.template）：核心路径、真实 payload、越权/分页/旧数据、P0/P1 Bug。 - 运行门禁：
boss runtime evaluate-gates <feature> <gate-name>（Gate 0/1，见references/quality-gate.md）。无 CLI 时按references/no-cli-fallback.md记录门禁结果到 STATE.md。 - 门禁失败不得宣布通过（不变量 4）。输出：测试摘要、覆盖率、门禁结果、未过项、下一步（可接
/boss:ship）。
用法
/boss:qa # 对当前项目跑测试 + 门禁
/boss:qa user-auth # 对已有 feature 跑 QA
选项
| 参数 | 说明 |
|---|---|
--lang <zh|en> |
QA 报告语言（默认 zh） |
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 · 42 lines · 49 tokens per session scan A 42a6063220bf
boss:qa is a command published in the GitHub repository echoVic/boss-skill (553 stars, last pushed 4d ago), licensed MIT. It adds 49 tokens to every session and 636 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 2026-08-30.
Other commands, from other repositories
upgrade
Upgrade the skillshare CLI binary and/or the built-in skillshare skill.
tokenless-stats
Show Tokenless compression statistics.
release
Walk the llmwiki release process step by step.
add-agent
引导新增一个 Agent 适配器。用法 /add-agent.
migrate
Command "migrate" from chohra-med/expo_boilerplate, covering invocation, steps and rule.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.