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 skills/stevesolun/micro-skills/convertednpx skills add stevesolun/micro-skills --skill convertedgit clone --depth 1 https://github.com/stevesolun/micro-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/stevesolun/micro-skills/converted)<a href="https://agentmods.dev/skills/stevesolun/micro-skills/converted"><img src="https://agentmods.dev/badge/skills/stevesolun/micro-skills/converted.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 5.1 | $0.00047 | $0.00285 |
| Opus 5 | $0.00023 | $0.00143 |
| Sonnet 5 | $0.00009 | $0.00057 |
| Haiku 4.5 | $0.00005 | $0.00028 |
Grade A, and why
api-crud-generator 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 6d 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
API CRUD Generator
When this skill triggers, execute the following gated pipeline. One step at a time. Do NOT skip ahead.
Pipeline
- Scope -- Read
references/01-scope.md. Detect stack, define resource. - Plan -- Read
references/02-plan.md. Map endpoints, auth, and file layout. - Build -- Read
references/03a-build-endpoints.mdthenreferences/03b-build-infra.md. Generate code. - Check -- Read
references/04-check.md. Answer every gate question YES or NO. Any NO = fix. - Deliver -- Read
references/05-deliver.md. Finalize and present.
Failure Log
Read failure-log.md before starting. Every pattern is a mandatory constraint.
Rules
- Read each reference file when you reach that step, not all at once.
- Step 4 (Check) is the hard gate. "Mostly yes" counts as NO.
- On Check failure: fix, re-run full checklist, append pattern to
failure-log.md.
What ships with it
8 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.
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.
- 6d ago First seen · 28 lines · 47 tokens per session scan A e932c7875ced
api-crud-generator is a skill published in the GitHub repository stevesolun/micro-skills (11 stars, last pushed 5mo ago), licensed MIT. It adds 47 tokens to every session and 285 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 skills, from other repositories
pace-change
Use when user says "不做了", "搁置", "停掉", "加一个", "加需求", "追加", "改需求", "需求变了", "范围变了", "优先级调", "延后", "提前", "砍掉", "先做这个", "排到前面", "恢复", "捡回来", "pace-change", or wants to add, pause, resume, reprioritize, modify, undo, batch change, or query change history. NOT for code implementation (/pace-dev) or project init (/pace-init).
pace-release
Use when user says "发布", "部署", "上线", "release", "pace-release", or wants to create, deploy, or close a release. NOT for CI/CD pipeline management (use /pace-sync). NOT for code implementation (use /pace-dev).
pace-retro
Use when user says "回顾", "复盘", "度量", "retro", "总结", "数据分析", "DORA", "质量报告", "交付效率", "度量报告", "趋势", "中期检查", "对比", "预测", "forecast", "能按时交付吗", "交付概率", "瓶颈", "pace-retro", or at iteration end when reviewing progress and metrics. NOT for next-step recommendations (use /pace-next). NOT for current status overview (use…
pace-guard
Use when user wants to assess risks before development, check current risk status, analyze risk trends, or says "风险/预检/预分析/guard/risk/隐患/安全检查". Also auto-invoked during advance mode intent checkpoint for L/XL CRs. NOT for /pace-dev (implementation), NOT for /pace-review (quality gate), NOT for /pace-test (testing).
pace-sync
Use when user says "同步/sync/同步到GitHub/关联Issue/unlink/Gate同步/sub-issue/全量同步/增量同步" or /pace-sync. Syncs Epic/BR/PF/CR to GitHub Issues. NOT for internal state (use /pace-dev).
pace-next
Use when user asks "下一步做什么", "接下来做什么", "该做什么", "什么最重要", "应该先做哪个", "最紧急", "优先级", "推荐做什么", "为什么推荐这个", "pace-next", or wants a recommendation for the most important next action across all domains. NOT for current progress overview (use /pace-status).