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 conorbronsdon/agent-skills --skill skill-creatorgit clone --depth 1 https://github.com/conorbronsdon/agent-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/conorbronsdon/agent-skills/skill-creator)<a href="https://agentmods.dev/skills/conorbronsdon/agent-skills/skill-creator"><img src="https://agentmods.dev/badge/skills/conorbronsdon/agent-skills/skill-creator.svg" alt="Measured on agentmods" 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 | $0.00053 | $0.01719 |
| Opus 5 | $0.00026 | $0.00860 |
| Sonnet 5 | $0.00011 | $0.00344 |
| Haiku 4.5 | $0.00005 | $0.00172 |
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 8d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skill-creator — Build New Skills Fast
Takes a plain-language description of a task and generates a ready-to-ship skill. The design goal is skills that are cheap in ambient context and current with the skill spec — most skill-creator skills in the wild fail on exactly those two axes: they don't know about arguments/argument-hint, never suggest disable-model-invocation, and write bloated descriptions that tax every session.
When to Use
- "I want a skill that does X"
- "Build me a slash command for Y"
- "Add a skill for [recurring task I do]"
Before You Start
Read:
- reference.md — snapshot of the current frontmatter spec, argument substitutions, and invocation/context-loading behavior. Check its snapshot date first: if older than 3 months, warn the user and continue with the pinned snapshot — don't re-fetch or modify the reference mid-generation. Spec updates are maintenance, not a side effect of building a skill: the canonical copy at agent-skill-builder has weekly spec-drift CI that opens an issue on upstream changes; sync from there, or update on an explicit ask.
- The host repo's
CLAUDE.mdand existing skills — avoid duplicating a skill that already exists, and match local conventions.
Instructions
1. Clarify the skill
Ask (or infer from context):
- Name: lowercase, hyphenated. The directory name under
.claude/skills/is the command you type; frontmatternameis only a display label. - Who invokes it — this is the most important design decision:
- User-only (side effects, or timing the user controls: publish, send, deploy, log) →
disable-model-invocation: true. Bonus: the description is then not loaded into every session — zero ambient context cost. - Claude-only (background knowledge, not an action) →
user-invocable: false. - Both (default) → the description must carry the trigger keywords, and it becomes a permanent per-session context cost. Make it earn that.
- User-only (side effects, or timing the user controls: publish, send, deploy, log) →
- Arguments: does the user pass input on the command line? If yes: set
argument-hint, and use$ARGUMENTS(or$0/$1, or namedarguments:) in the body. Don't make Claude guess what the trailing text means. - Input/Output: what does it read (files, MCP data, live command output), what does it produce?
- Tools:
allowed-toolsis a pre-approval grant (no permission prompts while active), not a restriction — scope entries tightly, e.g.Bash(git add *)notBash. Usedisallowed-toolsto actually remove tools. - Where it runs: inline (default — shares conversation context) or
context: fork+agent:for isolated, self-contained tasks. Fork only works when the body is an explicit task, not reference guidelines. - Data at load time: use dynamic context injection (
!`command`at line start) to inline live data (a diff, a status file) before Claude reads the skill. - Only set
model/effortoverrides with a specific reason. Usepaths:for skills scoped to certain files.
What ships with it
2 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.
- 8d ago First seen · 96 lines · 53 tokens per session scan A d1dc610c1928
skill-creator is a skill published in the GitHub repository conorbronsdon/agent-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 1,719 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 2026-08-31.
Other skills, from other repositories
mulmoterminal-dirs
Colour-code and order the directories you actually work in, from wherever you are. Writes each project's /.mulmoterminal.json — name badge, project icon image, the seven chrome colours, xterm palette (theme / colors), terminal font size, orderPriority (where it sits in the grid and in the launcher's chips), and…
mulmoterminal-keys
Bind keyboard shortcuts and fix keyboard/clipboard behaviour in MulmoTerminal. Writes keymap, which Settings cannot set at all — its Keyboard shortcuts section is read-only, listing every action bound or not plus a send row. Explains copyOnSelect, questionPaneEnabled and terminalSubmit, which have their own Settings…
tokf-discover
Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.
lamina-product-discovery
Frame product problems and decide what to build. Use when establishing business context, aligning actors with conflicting goals, discovering or prioritizing features, defining traceable requirements, comparing consequential tradeoffs, or recording a product decision. Use lamina-ux for interaction details and…
dashiai-ppt
A presentation-making add-on that creates an HTML slide deck from preset visual page designs. The result can open offline in a browser and can be exported as a PowerPoint or PDF file.
xiaohongshu-image-creator
An image-making assistant for Xiaohongshu, a Chinese social platform for lifestyle, product, and educational posts. It creates vertical covers and supporting images matched to the post’s topic, audience, and visual style.