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 Cap-go/capgo-skills --skill skill-creatorgit clone --depth 1 https://github.com/Cap-go/capgo-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/cap-go/capgo-skills/skill-creator)<a href="https://agentmods.dev/skills/cap-go/capgo-skills/skill-creator"><img src="https://agentmods.dev/badge/skills/cap-go/capgo-skills/skill-creator/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/cap-go/capgo-skills/skill-creator"><img src="https://agentmods.dev/badge/skills/cap-go/capgo-skills/skill-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk 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 | $0.00172 | $0.01843 |
| Opus 5.5 | $0.00069 | $0.00737 |
| Sonnet 5.5 | $0.00034 | $0.00369 |
| Haiku 4.5 | $0.00017 | $0.00184 |
Grade A, and why
skill-creator 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 14d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Authoring
Write skills that load at the right moment, teach what the model does not already know, and prove their own results.
When to Use
TRIGGER when:
- The user creates a skill directory, or asks to improve, review, or split an existing skill.
- A skill triggers too often, too rarely, or collides with a sibling skill.
bun run lint-skillsfails, or a skill must be registered in a plugin or the marketplace.- The user wants a skillgrade eval for a skill.
Do not use when:
- The user is writing app docs, a README, a changelog, or marketing copy.
- The user is editing library or plugin source that is not a skill.
Reference Index
Only load a reference when its topic is in play.
| File | Load when |
|---|---|
references/repo-layout.md |
Adding, renaming, or registering a skill in this repository, mirroring into plugins/, or reading lint errors |
references/authoring-patterns.md |
Writing the body: trigger design, reference index, traps, verification, version tags, subagent skills, inline snapshots |
Procedure
1. Scope the skill
- Write one sentence: "Load this when , so the agent can ."
- List the sibling skills that could also match. Each one becomes a negative trigger.
- Split the skill if it covers two unrelated workflows. Merge it if it would be a one-paragraph stub.
- Ask the user at real judgement calls (scope, audience, which product to prefer). Do not ask about things you can read from the repo.
2. Write the frontmatter
---
name: my-skill # lowercase, hyphenated, equals the folder name
description: <what it does>. Use when <symptoms, APIs, file names, error strings>. Do not use for <case> (sibling-skill).
---
- The description is the only text the router sees. Put concrete triggers in it: command names, config keys, file names, exact error strings. Name the sibling skills in the negative clause.
- Keep it to one line and at most 1024 characters (lint enforces both).
- Optional
when_to_use:is appended todescriptionin Claude Code's skill listing. The combined text is truncated at 1,536 characters, so put the key use case first. Other agents ignore it, so never move the core trigger out ofdescription. allowed-tools:only when the skill runs inline commands. Keep it minimal and read-only.
What ships with it
6 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.
- 14d ago Changed · +42 lines · +115 tokens per session 9192a070ffac
- 1mo ago First seen · 78 lines · 57 tokens per session scan A 5cf31e5899f1
skill-creator is a skill published in the GitHub repository Cap-go/capgo-skills (73 stars, last pushed 7d ago), licensed MIT. It adds 172 tokens to every session and 1,843 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
cf-cli
Cloudflare's official cf CLI (beta) for the public Cloudflare API and Workers projects. Use for finding and running Cloudflare commands from the terminal — sign-in and profiles, cf cli search, cf schema, cf deploy/dev/build, resource commands for DNS, zones, D1, KV, and R2 — and for choosing between cf and Wrangler in…
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
find-journalists
Build a researched, fit-checked journalist list for a specific PR campaign. Prefer Medialyst's asynchronous media-list research workflow when available, with explicit approval before credit spend; otherwise produce a best-effort local list with only publicly listed, source-cited contacts.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
ai-visibility-writing
Audit, question, suggest, or fact-preservingly revise a press release, blog post, contributed article, or expert explainer so AI answer systems can more easily retrieve, understand, quote, and cite its useful information. Use when someone asks for AI visibility, AI search, answer-engine, AEO, GEO, AI Overview, or…