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/vinvcn/addyosmani-agent-skills-zhWrote 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/vinvcn/addyosmani-agent-skills-zh/constraints)<a href="https://agentmods.dev/commands/vinvcn/addyosmani-agent-skills-zh/constraints"><img src="https://agentmods.dev/badge/commands/vinvcn/addyosmani-agent-skills-zh/constraints/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/commands/vinvcn/addyosmani-agent-skills-zh/constraints"><img src="https://agentmods.dev/badge/commands/vinvcn/addyosmani-agent-skills-zh/constraints.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 | $0.00020 | $0.00726 |
| Opus 5.5 | $0.00008 | $0.00290 |
| Sonnet 5 | $0.00004 | $0.00145 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade A, and why
constraints 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 12d 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
调用 agent-skills:constraint-driven-development skill。
$ARGUMENTS
不带参数时的默认行为：为本仓库设置 constraints。
-
先检测。 读取 package.json / pyproject.toml / go.mod、test runner、现有 lint configs、当前 coverage 输出、CI workflows，以及正在使用的 agent harness。用两行汇报你的发现。绝不询问任何你自己能读到的东西。
-
访谈，最多四个问题。 一次一个，每个都附上你的最佳猜测和一个可用的默认值，让 "我不知道" 也能产出一份能用的配置：
- 除了 floor 之外还要哪些维度（coverage、security、performance、accessibility、architecture）
- 任务中途某项检查失败时，是 block 还是 warn
- 目标数值，还是测量今天的值并守住它们
- 在把工作交还给人之前，能容忍的最慢一次检查
-
在仓库根目录编写 CONSTRAINTS.md，包含 Floor 部分、被强制执行的数值、仅测量类指标及其今日数值，以及一张带 owner 和到期日期的 exceptions 表。每个数值都需要给出陈述过的理由。
-
为每个选中的维度安装所需工具。 一个维度有数值却背后没有工具，那只是愿望。使用事实标准工具，让现有配置继续可用：代码扫描用 Semgrep，secrets 用 gitleaks（始终带
--redact），依赖用 osv-scanner，accessibility 用 axe-core，web vitals 用 Lighthouse，bundles 用 size-limit，boundaries 用 dependency-cruiser，断言质量用 Stryker。在 CONSTRAINTS.md 中把确切命令记录在每条规则旁边。Accessibility 和 performance 需要一个可运行的 URL；如果项目没有，如实说明并舍弃该维度，而不是编造一项检查。把这些命令作为 check:fast / check:task / check:full 添加到 package.json。 -
按成本摆放每项检查。 Types、lint 和 secrets 放在 edit loop 里（秒级）。相关 tests 和 changed-line coverage 放在任务结束时（90 秒以内）。其余全部放在 review 或 CI 中。检查范围限定在 diff，而不是整个仓库。
-
让 agent 指向它。 在 CLAUDE.md 中加一行，告诉 agents 阅读 CONSTRAINTS.md，且绝为了让某个变更通过而弱化它。
-
验证。 对当前分支运行这些 constraints。如果某项失败而用户不同意，现在就修 constraint，而不是留下一个人们会学着无视的门禁。
子命令：
/constraints check— 对当前分支运行现有 constraints 并报告/constraints guard— 在 diff 中检查被弱化的标准：调低的阈值、被跳过或删除的 tests、新增的 suppression 注释、未完成的 stubs、新增的 exceptions/constraints ratchet— 把今天的测量值记录为不得下降的 floor
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.
- 12d ago First seen · 33 lines · 20 tokens per session scan A 72f1435020e8
constraints is a command published in the GitHub repository vinvcn/addyosmani-agent-skills-zh (36 stars, last pushed 13d ago), licensed MIT. It adds 20 tokens to every session and 726 once invoked, about $0.0001 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 2026-09-16.
Other commands, from other repositories
test
Run TDD workflow — write failing tests, implement, verify. For bugs, use the Prove-It pattern.
test
Run TDD workflow — write failing tests, implement, verify. For bugs, use the Prove-It pattern.
ship
Run the pre-launch checklist via parallel fan-out to specialist personas, then synthesize a go/no-go decision.
plan
Break work into small verifiable tasks with acceptance criteria and dependency ordering.
build
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.
webperf
Run a web performance audit via the web-performance-auditor persona.