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 agentmods add skills/stacklok/toolhive-studio/skill-creatornpx skills add stacklok/toolhive-studio --skill skill-creatorgit clone --depth 1 https://github.com/stacklok/toolhive-studioWhat 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 | $0.00040 | $0.00712 |
| Opus 5 | $0.00020 | $0.00356 |
| Sonnet 5 | $0.00008 | $0.00142 |
| Haiku 4.5 | $0.00004 | $0.00071 |
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 2d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator
Create AI agent skills that work across Claude Code, Codex, and Cursor.
Workflow
- Claude is canonical - Always create/edit in
.claude/skills/<name>/first - Replicate with CLI - Copy to
.codex/skills/and.cursor/skills/usingcp -r - Format differences - Use
sedonly if agent-specific tweaks are needed (rare)
Directory Structure
.claude/skills/<skill-name>/
├── SKILL.md # Required - instructions + metadata
├── references/ # Optional - supporting documentation
├── scripts/ # Optional - executable helpers
└── assets/ # Optional - templates, resources
.codex/skills/<skill-name>/ # Copy of Claude's
.cursor/skills/<skill-name>/ # Copy of Claude's
SKILL.md Format
---
name: skill-name # Required: lowercase, hyphens, max 64 chars
description: What it does... # Required: triggers auto-selection by agent
allowed-tools: Read, Grep, Bash # Optional: Claude-specific (ignored by others)
model: claude-opus-4-5-20251101 # Optional: Claude-specific (ignored by others)
---
# Skill Title
Instructions in markdown...
Required Fields
name: Lowercase with hyphens, must match directory namedescription: Explains what the skill does and when to use it. Include keywords users would say to help the agent auto-select this skill.
Optional Fields (Claude-specific, ignored by other agents)
allowed-tools: Tools the agent can use without asking permissionmodel: Override the model for this skillcontext: fork: Run in isolated subagent context
Creating a New Skill
- Ask the user what the skill should do
- Choose a descriptive name (lowercase, hyphens)
- Create the Claude skill:
mkdir -p .claude/skills/<name> - Write
.claude/skills/<name>/SKILL.mdwith proper frontmatter - Replicate to other agents:
cp -r .claude/skills/<name> .codex/skills/ cp -r .claude/skills/<name> .cursor/skills/
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.
- 2d ago First seen · 84 lines · 40 tokens per session scan A 38ee7f6d21d8
skill-creator is a skill published in the GitHub repository stacklok/toolhive-studio (163 stars, last pushed 4d ago), licensed Apache-2.0. It adds 40 tokens to every session and 712 once invoked, about $0.0002 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.
Other skills, from other repositories
training-guide
Build an interactive visual course as one self-contained HTML page, one idea per screen. Use to explain or teach a subject visually, step by step.
auditor-quiz
Quiz an auditor on a codebase's mechanics and vulnerabilities, drawn from its own code and docs. Use to test understanding before or during a review.
context-window-to-skill
Takes the active conversation as reference to understand how a skill can be created, with all the lessons learned from the user's needs in the conversation.
document
Workflow Phase 10 — orchestrator for documentation work. Surveys the diff, routes any page on a documentation surface through technical-writer, standalone technical reference through the documentation skill, tutorials through technical-tutorials, and all other prose body work (inline docs, README updates, user-facing…
skills:validate
Validate skill files meet the standard format and naming conventions.
harn-control-events
Make an agent session answer stop and steer promptly, kill what it started, and leave a record that names the control.