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 skills add Linfee/spec-kit-cn --skill release-post-verifygit clone --depth 1 https://github.com/Linfee/spec-kit-cnWrote 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/skills/linfee/spec-kit-cn/release-post-verify)<a href="https://agentmods.dev/skills/linfee/spec-kit-cn/release-post-verify"><img src="https://agentmods.dev/badge/skills/linfee/spec-kit-cn/release-post-verify/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/skills/linfee/spec-kit-cn/release-post-verify"><img src="https://agentmods.dev/badge/skills/linfee/spec-kit-cn/release-post-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 47 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 48 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
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 | $0.00069 | $0.00782 |
| Opus 5.5 | $0.00028 | $0.00313 |
| Sonnet 5.5 | $0.00014 | $0.00156 |
| Haiku 4.5 | $0.00007 | $0.00078 |
Grade A, and why
release-post-verify 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 1mo 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
发布后本地验收
这个 skill 只用于手动触发，不应自动执行。
目标
验证 specify-cn 的 main 分支最新提交是否满足以下条件：
- 安装到的是目标最新版
- CLI 输出仍然是中文
- 对全部支持的 agent 都能成功执行
init .specify/templates、.specify/memory、脚本目录完整- agent 命令/工作流/提示文件落在正确位置
--ai-skills模式下，skills 安装在正确位置且内容基本正确
使用方式
默认全量执行：
python3 .claude/skills/release-post-verify/validate_release_post.py
常用变体：
# 仅跑部分 agent
python3 .claude/skills/release-post-verify/validate_release_post.py --agents claude copilot q
# 保留临时目录
python3 .claude/skills/release-post-verify/validate_release_post.py --keep-temp
# 跳过 ai-skills 或 PowerShell 抽样
python3 .claude/skills/release-post-verify/validate_release_post.py --skip-ai-skills --skip-ps-sample
执行要求
- 先读取脚本输出，不要手工猜测 agent 列表；脚本会从仓库源码中的
AGENT_CONFIG动态取值。 - 必须通过远端
main分支最新提交运行，禁止回退到本地源码、本地 wheel 或当前工作区环境：- 首选
uvx --isolated --from git+https://github.com/linfee/spec-kit-cn@main specify-cn - 失败时再尝试
uv tool run --isolated --from git+https://github.com/linfee/spec-kit-cn@main specify-cn - 任何情况下都不能使用
uv run specify-cn、本地 editable 安装、仓库内 wheel 文件或本地路径依赖代替发布包
- 首选
- 脚本会优先复用现有
GH_TOKEN/GITHUB_TOKEN，否则尝试读取gh auth token，并自动传给需要访问 GitHub API 的命令。 - 所有初始化必须在临时目录进行，不要把验证产物写回仓库。
- 默认应跑完整轮，即使某个 agent 失败，也继续其余 agent，最后统一汇总。
- 若脚本返回非零退出码，不要宣称验证通过；先根据报告定位失败项。
输出解读
脚本会输出：
- 使用的 runner
- 目标版本
- 临时目录位置
- JSON 报告路径
- 每个 agent 的
normal-init/ai-skills-init/powershell-sample状态
如果失败，临时目录会自动保留，便于继续排查。
完成时的回复要求
完成后只给用户简短结论，至少包含：
- 是否通过
- 失败的 agent 或失败类别
- 临时目录或报告路径（若失败）
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 74 lines · 69 tokens per session scan A eb048dfb5790
release-post-verify is a skill published in the GitHub repository Linfee/spec-kit-cn (708 stars, last pushed 2mo ago), licensed MIT. It adds 69 tokens to every session and 782 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.