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 vidhunnan/agentic-skills --skill skill-scaffoldgit clone --depth 1 https://github.com/vidhunnan/agentic-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/vidhunnan/agentic-skills/skill-scaffold)<a href="https://agentmods.dev/skills/vidhunnan/agentic-skills/skill-scaffold"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/skill-scaffold/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/vidhunnan/agentic-skills/skill-scaffold"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/skill-scaffold.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 | $0.00201 | $0.05152 |
| Opus 5 | $0.00101 | $0.02576 |
| Sonnet 5 | $0.00040 | $0.01030 |
| Haiku 4.5 | $0.00020 | $0.00515 |
Grade A, and why
skill-scaffold 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 10d 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 — 420 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skill-scaffold
Adds a skill to this library. Not the skill's logic — its plumbing: the eight
places a new skill has to appear before it installs, triggers, and shows up on the
site, plus the house SKILL.md skeleton every skill here shares.
The shape of a skill in this repo lives nowhere except in the existing SKILL.md
files. Every new author — including a future session of Claude — reconstructs it by
reading and imitating, and imitation drifts. This skill exists to hold that shape in
one place.
Two rules govern it:
- Scaffold, never generate. It writes headings, frontmatter and registrations. It does not write the Steps that make a skill worth installing. A scaffold that invents behaviour produces a plausible skill that does nothing — strictly worse than an obvious stub, because nobody notices the stub is empty until it fails in front of a user.
- The description is the product.
descriptionis the auto-invocation matcher. A skill whose description reads beautifully and matches nothing a user would actually type is broken, and broken silently. So the trigger phrases are interviewed, never invented, and the assembled description is shown back before it is used.
The eight touchpoints
Adding a skill means all eight. This list has been wrong twice, in the same direction — it omitted the website, and then it omitted the build. Both omissions had the same shape: a step that lives outside the obvious files, so nobody remembers it and nothing complains until later.
| # | Path | What lands there |
|---|---|---|
| 1 | docs/prds/<name>.md |
The spec, from docs/prds/_TEMPLATE.md |
| 2 | skills/<name>/SKILL.md |
Frontmatter + the house skeleton |
| 3 | skills/<name>/.claude-plugin/plugin.json |
name, description, version, author |
| 4 | .claude-plugin/marketplace.json |
One entry, source: ./skills/<name> |
| 5 | README.md — Skills tables |
One row, in the right group |
| 6 | README.md — Install block |
One /plugin install <name> line |
| 7 | website/components/lib/skills.ts |
One Skill object inside the right SkillGroup |
| 8 | cd website && npm run prebuild |
Regenerated zips, manifest.json and counts.json — committed build output |
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.
- 10d ago First seen · 420 lines · 201 tokens per session scan A d42aca05b7a1
skill-scaffold is a skill published in the GitHub repository vidhunnan/agentic-skills (2 stars, last pushed 4d ago), licensed MIT. It adds 201 tokens to every session and 5,152 once invoked, about $0.0010 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 2026-08-31.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…