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 didacrios/ai-coding-protocols --skill skill-generatorgit clone --depth 1 https://github.com/didacrios/ai-coding-protocolsWrote 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/didacrios/ai-coding-protocols/skill-generator)<a href="https://agentmods.dev/skills/didacrios/ai-coding-protocols/skill-generator"><img src="https://agentmods.dev/badge/skills/didacrios/ai-coding-protocols/skill-generator/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/didacrios/ai-coding-protocols/skill-generator"><img src="https://agentmods.dev/badge/skills/didacrios/ai-coding-protocols/skill-generator.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 | $0.00067 | $0.01364 |
| Opus 5.5 | $0.00027 | $0.00546 |
| Sonnet 5.5 | $0.00013 | $0.00273 |
| Haiku 4.5 | $0.00007 | $0.00136 |
Grade A, and why
skill-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 20d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Generator
A meta-skill for creating project-specific skills as a codebase evolves. New modules, recurring patterns, and adopted libraries each carry conventions worth capturing; this skill decides whether to capture them, and how.
When to activate
- A significant new module or feature introduces conventions no existing skill covers
- A pattern recurs across two or more files and is likely to recur again
- A new integration, library, or framework is adopted
- The user asks to generate or create a skill
Core concepts
- Skills are instructional, not executable — they steer agent behavior through precise prose, not runnable code.
- Recurrence threshold — do not create a skill for a one-off pattern; wait until it appears in at least two or three places.
- Composition over duplication — reference existing skills instead of restating them.
- Generated once, maintained after — a skill that drifts from the code is worse than no skill.
Layout
Paths below are relative to the skills root: the directory that holds the installed skills. The skills CLI installs to <project>/.agents/skills/ (project scope) or ~/.agents/skills/ (global), and vendoring writes into the same project path. Detect the root from the environment rather than assuming it, but .agents/skills/ is the one to expect.
Project-specific skills live in a project/ subdirectory of that root:
<skills-root>/
├── recursive-exploration/SKILL.md ← installed generic skills
├── typescript-standard/SKILL.md
└── project/ ← yours; survives re-install and re-vendoring
└── {domain}/SKILL.md
Keeping project skills under project/ is what makes re-installing or re-vendoring the generic skills safe.
Process
1. Verify the trigger
Confirm at least one holds:
- New module or feature — a distinct area (an API layer, a component system, a queue worker) with its own conventions.
- Recurring pattern — the same approach has appeared in 2+ places and will likely appear again.
- New dependency — a library or service that requires specific usage patterns.
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.
- 20d ago Changed · +18 lines · +49 tokens per session c429fa982fea
- 1mo ago Changed 6413a4a2888a
- 2mo ago First seen · 129 lines · 18 tokens per session scan A 994eb13b20be
skill-generator is a skill published in the GitHub repository didacrios/ai-coding-protocols (2 stars, last pushed 5d ago), licensed MIT. It adds 67 tokens to every session and 1,364 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 2026-08-31.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…