skill-creator

skill-creator is a skill for Claude Code, Codex from joe-broadhead/open-cowork. It costs 26 tokens per session (474 once invoked), scanned A, original, MIT.

Instructions for designing and writing reusable OpenCode skill bundles. A skill bundle is a package of guidance, usually starting with a SKILL.md file, that teaches an agent how to handle a specific workflow.

In plain words
What is it for?
Use it to create or update a skill, choose its identifier, write its main instructions, and decide whether it needs examples, templates, or reference files.
Why use it?
It turns an informal workflow into a consistent package with clear activation rules, tools, files, and safety limits.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions OpenCode.

Good fit Use it to create or update a skill, choose its identifier, write its main instructions, and decide whether it needs examples, templates, or reference files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joe-broadhead/open-cowork/skill-creator
Install

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.

Any agent
npx skills add joe-broadhead/open-cowork --skill skill-creator
Clone the repo
git clone --depth 1 https://github.com/joe-broadhead/open-cowork

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for skill-creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/joe-broadhead/open-cowork/skill-creator/github.svg)](https://agentmods.dev/skills/joe-broadhead/open-cowork/skill-creator)
Your own site
<a href="https://agentmods.dev/skills/joe-broadhead/open-cowork/skill-creator"><img src="https://agentmods.dev/badge/skills/joe-broadhead/open-cowork/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.

agentmods 80×15 button for skill-creator

Your own site · 80×15
<a href="https://agentmods.dev/skills/joe-broadhead/open-cowork/skill-creator"><img src="https://agentmods.dev/badge/skills/joe-broadhead/open-cowork/skill-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 474 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.00474
Opus 5 $0.00013 $0.00237
Sonnet 5 $0.00005 $0.00095
Haiku 4.5 $0.00003 $0.00047

Measured 11d ago against content hash 6784b9efe41a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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 11d 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.

skills/skill-creator/SKILL.md · 60 lines

What it actually says

Skill Creator

Use this skill when a user wants to create or update an OpenCode skill for Open Cowork.

Purpose

  • Turn a rough workflow idea into a reusable skill bundle.
  • Keep the skill aligned with the OpenCode skill standard: one SKILL.md entrypoint plus optional extra files.
  • Add extra files only when they materially improve the skill, such as templates, examples, references, or helper assets.

Workflow

  1. Confirm the skill's job:
    • what it helps with
    • when it should be used
    • what tools it expects or teaches
  2. Choose a clean skill id:
    • lowercase
    • hyphenated
    • stable and descriptive
  3. Draft SKILL.md with:
    • frontmatter name
    • frontmatter description
    • a short purpose section
    • a workflow section
    • tool guidance if relevant
    • guardrails if misuse is likely
  4. Decide whether the bundle needs extra files:
    • references/*.md for longer usage notes
    • examples/*.md for worked examples
    • templates/* for reusable output scaffolds
    • avoid extra files if the skill is simple enough to live in SKILL.md
  5. Use the skills MCP tools to save the bundle:
    • skills_get_skill_bundle before editing an existing skill
    • skills_save_skill_bundle to create or update the bundle
    • skills_list_skill_bundles to inspect what already exists
  6. Summarize what was created:
    • skill id
    • main purpose
    • any extra files added

Guardrails

  • Do not create vague skills that duplicate general assistant behavior.
  • Prefer one focused skill over a broad catch-all.
  • Keep instructions operational and reusable.
  • If a skill depends on a tool or MCP, state that clearly.
  • If no extra files are needed, do not invent them.

Output

  • Brief explanation of the skill’s purpose.
  • The saved skill id.
  • A short note on any supporting files added to the bundle.
Changes

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.

  1. 11d ago First seen · 60 lines · 26 tokens per session scan A 6784b9efe41a

Subscribe to this mod's changes

skill-creator is a skill published in the GitHub repository joe-broadhead/open-cowork (11 stars, last pushed 6d ago), licensed MIT. It adds 26 tokens to every session and 474 once invoked, about $0.0001 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.