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 michaelChe956/Cadence-skills --skill pre-checkgit clone --depth 1 https://github.com/michaelChe956/Cadence-skillsWrote 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/michaelche956/cadence-skills/pre-check)<a href="https://agentmods.dev/skills/michaelche956/cadence-skills/pre-check"><img src="https://agentmods.dev/badge/skills/michaelche956/cadence-skills/pre-check/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/michaelche956/cadence-skills/pre-check"><img src="https://agentmods.dev/badge/skills/michaelche956/cadence-skills/pre-check.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 | $0.00055 | $0.01311 |
| Opus 5 | $0.00028 | $0.00656 |
| Sonnet 5 | $0.00011 | $0.00262 |
| Haiku 4.5 | $0.00006 | $0.00131 |
Grade A, and why
pre-check 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.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
前置条件检查
概述
本 Skill 通过关联脚本完成前置条件检查、OpenSpec 客户端产物补齐、Superpowers 同步和结构化复核。模型侧只负责定位脚本、在项目根调用一次脚本,以及读取报告并向用户呈现结果;确定性的安装、写入、同步和验证均由脚本处理。
脚本默认不收集任何私密信息,也不修改用户全局配置。run 可能在项目根写入 OpenSpec 客户端产物,并在需要时准备 Superpowers 来源及其技能链接;check 仅探测,不执行写入。Playwright 默认不启用,只有用户明确要求时才可选择。
参数边界
- 参数中的完整 token
no-interrupt或--no-interrupt表示无人工中断模式。 - 普通模式和
--no-interrupt模式的失败语义不同,不能混用。 - 不询问、不收集、不验证 API Key、Token 或密码;真实密钥由用户自行在后续配置中替换占位符。
unsupported必须明确报告为需要人工处理,不静默改由模型自由编排。
执行契约
步骤 1:定位 skill 目录与绝对路径
在项目根执行 pwd -P,记为 <PROJECT_ROOT>;从当前 skill 目录拼出 <PRE_CHECK_SH>=<skill-dir>/scripts/pre-check.sh。不要进入 skill 目录或复制脚本;脚本依赖同目录 scripts/mirrors/{default,cn}.sh。
步骤 2:在项目根一次调用脚本
仅执行一次与参数相符的命令:
cd "<PROJECT_ROOT>" && bash "<PRE_CHECK_SH>" run [--mirror cn] [--no-interrupt]
仅探测用 check;升级只在明确要求时添加 --upgrade。stdout 为一份 JSON,stderr 为中文摘要;不得自行改写安装、OpenSpec、Git 或软链命令。
脚本调用必须保持项目根 cwd。除显式传入的 --mirror cn、--no-interrupt 和 --upgrade 外,不自行拼接额外流程;报告文件由调用方按既有生命周期管理。
步骤 3:读取 JSON 报告并呈现
读取 overall、原有 steps[] 和五项 phases[],呈现 result/action/duration_ms/created/updated/skipped/conflicts;Superpowers phase 呈现 origin/branch/before_revision/after_revision。overall=success 且五阶段通过才报告完成;重跑以 phase skipped/all-skipped 和产物无变化证明幂等。
--no-interrupt 任一 phase failed 或脚本非零立即停止,报告失败原因、已完成 phase 和恢复建议;普通模式也不自行执行未覆盖写入。unsupported 必须报告人工处理,不静默回退模型自由编排。
Playwright 仅用户明确要求时 opt-in,未要求不安装、不写入。API Key 只展示 your_zhipu_api_key、your_minimax_api_key 占位符和安全提醒,不询问、不收集、不验证真实密钥。
报告与边界说明
脚本报告保留兼容的 steps[],并提供固定顺序的五项 phases[]:base-tools、openspec、superpowers-git、superpowers-links、verify。呈现 phase 时以脚本返回的 result 和计数为准,不根据模型侧猜测补写状态。
普通模式下,失败 phase 可被记录为 partial 并继续脚本规定的后续阶段,最终必须如实报告整体状态;这不表示成功,也不允许自行补做脚本未覆盖的写入。--no-interrupt 下失败立即阻断下游写入。阶段错误应说明失败原因、已完成 phase 和恢复建议。
软链拓扑以解析后最终等价为准:现网直连源路径、兼容中转链均视为同一有效拓扑;已有正确链接应保持幂等,非目标用户内容不得被触碰。冲突和不可支持的布局按报告语义转人工处理。
默认 Playwright 行为是跳过,不安装、不写入;只有用户明确提出浏览器自动化需求时才执行 opt-in。API Key 仅保留以下安全提醒:
- 智普配置使用
your_zhipu_api_key占位符。 - MiniMax 配置使用
your_minimax_api_key占位符。 - 不收集真实密钥,用户应自行替换占位符。
What ships with it
60 files 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.
- scripts/mirrors/cn.sh 1.0 KB runs code
- scripts/mirrors/default.sh 714 B runs code
- scripts/pre-check.sh 48 KB runs code
- scripts/test.sh 10 KB runs code
- tests/baselines/precheck-v2/README.md 3.3 KB
- tests/baselines/precheck-v2/tree.txt 17 KB
- tests/fixtures/base-tools-failure/README.md 152 B
- tests/fixtures/links-correct-direct/README.md 122 B
- tests/fixtures/links-correct-layered/README.md 165 B
- tests/fixtures/links-correct/README.md 188 B
- tests/fixtures/links-non-symlink-conflict/README.md 162 B
- tests/fixtures/links-pi-missing-cadence/README.md 162 B
- tests/fixtures/openspec-partial/project/.agents/skills/openspec-execute/SKILL.md 21 B
- tests/fixtures/openspec-partial/project/.claude/commands/opsx/.sentinel 22 B
- tests/fixtures/openspec-ready/project/.agents/skills/openspec-execute/SKILL.md 21 B
- tests/fixtures/openspec-ready/project/.agents/skills/openspec-update-change/SKILL.md 31 B
- tests/fixtures/openspec-ready/project/.claude/commands/opsx/.sentinel 22 B
- tests/fixtures/openspec-ready/project/.kimi-code/skills/openspec-brainstorm/SKILL.md 22 B
- tests/fixtures/openspec-ready/project/.kimi-code/skills/openspec-execute/SKILL.md 19 B
- tests/fixtures/openspec-ready/project/.kimi-code/skills/openspec-plan/SKILL.md 16 B
- tests/fixtures/openspec-ready/project/.kimi-code/skills/openspec-review/SKILL.md 18 B
- tests/fixtures/openspec-ready/project/.kimi-code/skills/openspec-update-change/SKILL.md 31 B
- tests/fixtures/openspec-ready/project/.kimi-code/skills/openspec-verify/SKILL.md 18 B
- tests/fixtures/openspec-ready/project/.pi/prompts/opsx-brainstorm.md 20 B
- tests/fixtures/openspec-ready/project/.pi/prompts/opsx-execute.md 17 B
- tests/fixtures/openspec-ready/project/.pi/prompts/opsx-plan.md 14 B
- tests/fixtures/openspec-ready/project/.pi/prompts/opsx-review.md 16 B
- tests/fixtures/openspec-ready/project/.pi/prompts/opsx-update-change.md 23 B
- tests/fixtures/openspec-ready/project/.pi/prompts/opsx-verify.md 16 B
- tests/fixtures/openspec-ready/project/.pi/skills/openspec-brainstorm/SKILL.md 20 B
- tests/fixtures/openspec-ready/project/.pi/skills/openspec-execute/SKILL.md 17 B
- tests/fixtures/openspec-ready/project/.pi/skills/openspec-plan/SKILL.md 14 B
- tests/fixtures/openspec-ready/project/.pi/skills/openspec-review/SKILL.md 16 B
- tests/fixtures/openspec-ready/project/.pi/skills/openspec-update-change/SKILL.md 31 B
- tests/fixtures/openspec-ready/project/.pi/skills/openspec-verify/SKILL.md 16 B
- tests/fixtures/openspec-wrong-pi-count/project/.agents/skills/openspec-execute/SKILL.md 21 B
- tests/fixtures/openspec-wrong-pi-count/project/.claude/commands/opsx/.sentinel 22 B
- tests/fixtures/openspec-wrong-pi-count/project/.kimi-code/skills/openspec-brainstorm/SKILL.md 22 B
- tests/fixtures/openspec-wrong-pi-count/project/.kimi-code/skills/openspec-execute/SKILL.md 19 B
- tests/fixtures/openspec-wrong-pi-count/project/.kimi-code/skills/openspec-plan/SKILL.md 16 B
- tests/fixtures/openspec-wrong-pi-count/project/.kimi-code/skills/openspec-review/SKILL.md 18 B
- tests/fixtures/openspec-wrong-pi-count/project/.kimi-code/skills/openspec-verify/SKILL.md 18 B
- tests/fixtures/openspec-wrong-pi-count/project/.pi/prompts/opsx-brainstorm.md 20 B
- tests/fixtures/openspec-wrong-pi-count/project/.pi/prompts/opsx-execute.md 17 B
- tests/fixtures/openspec-wrong-pi-count/project/.pi/prompts/opsx-extra.md 13 B
- tests/fixtures/openspec-wrong-pi-count/project/.pi/prompts/opsx-plan.md 14 B
- tests/fixtures/openspec-wrong-pi-count/project/.pi/prompts/opsx-review.md 16 B
- tests/fixtures/openspec-wrong-pi-count/project/.pi/prompts/opsx-verify.md 16 B
- tests/fixtures/openspec-wrong-pi-count/project/.pi/skills/openspec-brainstorm/SKILL.md 20 B
- tests/fixtures/openspec-wrong-pi-count/project/.pi/skills/openspec-execute/SKILL.md 17 B
- tests/fixtures/openspec-wrong-pi-count/project/.pi/skills/openspec-plan/SKILL.md 14 B
- tests/fixtures/openspec-wrong-pi-count/project/.pi/skills/openspec-review/SKILL.md 16 B
- tests/fixtures/openspec-wrong-pi-count/project/.pi/skills/openspec-verify/SKILL.md 16 B
- tests/fixtures/playwright-not-requested/README.md 148 B
- tests/fixtures/report-cleanup/README.md 129 B
- tests/fixtures/superpowers-non-git/project/.agents/skills/openspec-execute/SKILL.md 21 B
- tests/fixtures/superpowers-non-git/project/.agents/skills/openspec-update-change/SKILL.md 8 B
- tests/fixtures/superpowers-non-git/project/.claude/commands/opsx/.sentinel 22 B
- tests/fixtures/superpowers-non-git/project/.kimi-code/skills/openspec-brainstorm/SKILL.md 22 B
- tests/fixtures/superpowers-non-git/project/.kimi-code/skills/openspec-execute/SKILL.md 19 B
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 Changed · -372 lines scan D → A 2e5ee7bf52bf
- 12d ago First seen · 441 lines · 55 tokens per session scan D 0dd1971a6af9
pre-check is a skill published in the GitHub repository michaelChe956/Cadence-skills (11 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 1,311 once invoked, about $0.0003 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…