Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/MadAppGang/magusnpx agentmods add skills/madappgang/magus/skill-authoringWrote 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/madappgang/magus/skill-authoring)<a href="https://agentmods.dev/skills/madappgang/magus/skill-authoring"><img src="https://agentmods.dev/badge/skills/madappgang/magus/skill-authoring/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/madappgang/magus/skill-authoring"><img src="https://agentmods.dev/badge/skills/madappgang/magus/skill-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00054 | $0.01639 |
| Opus 5 | $0.00027 | $0.00820 |
| Sonnet 5 | $0.00011 | $0.00328 |
| Haiku 4.5 | $0.00005 | $0.00164 |
Grade A, and why
skill-authoring 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 5d 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.
Authoring a skill in this repo
A skill exists to give an agent procedural knowledge it would not reliably reproduce on its own. It has exactly two jobs, and they are separate:
| Part | Job | Read by |
|---|---|---|
description |
decide whether to load | every turn, for every installed skill |
SKILL.md body |
do the task correctly once loaded | only after it triggers |
The description is the only part with an always-on cost. Everything else is pay-as-you-go.
The one path
- Write the description (below). It is the highest-leverage text in the skill.
- Write the body: objective, inputs and outputs, the ordered workflow, decision points, failure modes, verification. One recommended path, imperative voice.
- Move conditional depth into
references/, each with an explicit loading instruction. - Choose the visibility. Read
references/visibility.md— this is where skills break. - Run
bun skills/skill-authoring/scripts/check-skill.ts <path>. Fix what it reports. - If the skill must trigger reliably, run the routing evaluation in
references/routing-eval.md.
The description
Capability first. Over budget, Claude Code shortens descriptions rather than dropping skills, so the tail is what disappears. Lead with what the skill does, not when.
<what it does, concretely>. Use when <intent, artifacts, phrasings a user actually types>.
Do not use for <the nearest sibling that competes>; use <that skill> instead.
The boundary clause is optional and costs characters. Add it only where a sibling genuinely competes for the same words. Two in a plugin is normal; five means the skills themselves overlap and the fix is a merge, not more prose.
Be slightly pushy. Models under-trigger. An "even if they only say X" clause catches indirect phrasing, and it earns its characters on disciplines nobody names out loud — nobody types "apply verification-before-completion".
Ceiling: 250 characters. This repo's limit, enforced by
scripts/skill-budget-check.ts in CI, and stricter than the portable 1,024. It is a
ratchet: lower it as descriptions improve, never raise it to make a build pass.
What ships with it
3 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.
- 5d ago First seen · 147 lines · 54 tokens per session scan A a64f8ef9c0ff
skill-authoring is a skill published in the GitHub repository MadAppGang/magus (9 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 1,639 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 2026-09-04.
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…