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 damionrashford/media-os --skill skill-creatorgit clone --depth 1 https://github.com/damionrashford/media-osWrote 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/damionrashford/media-os/skill-creator)<a href="https://agentmods.dev/skills/damionrashford/media-os/skill-creator"><img src="https://agentmods.dev/badge/skills/damionrashford/media-os/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/damionrashford/media-os/skill-creator"><img src="https://agentmods.dev/badge/skills/damionrashford/media-os/skill-creator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00080 | $0.02702 |
| Opus 5 | $0.00040 | $0.01351 |
| Sonnet 5 | $0.00016 | $0.00540 |
| Haiku 4.5 | $0.00008 | $0.00270 |
Grade C, and why
skill-creator scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf <output>/<name> How it starts
The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator
What you're building: $ARGUMENTS
Available scripts
scripts/scaffold.py— Creates skill folder + SKILL.md from template. Run this first.scripts/validate.py— Validates a skill against spec requirements. Run after writing.scripts/init-evals.py— Scaffoldsevals/withevals.json+trigger-queries.jsontemplates.scripts/test-triggers.py— Runs trigger queries through claude CLI, reports trigger rates.scripts/run-eval.py— Runs a single eval case (with-skill or without) via claude CLI.scripts/grade.py— Grades assertions against outputs, writesgrading.json+benchmark.json.
Phase 1 — Gather what you need
Ask the user these questions up front (all at once):
- What task or workflow should the skill handle? What does the user type that should trigger it?
- Who invokes it — you, Claude, or both?
- User-only (deploy, commit, send slack) →
--disable-model-invocation - Claude-auto only → will set
user-invocable: falsein body - Both → default, no flag
- User-only (deploy, commit, send slack) →
- Personal or project-scoped?
- Personal (all your projects):
~/.claude/skills - Project-only:
.claude/skills
- Personal (all your projects):
- Does it need scripts? Reusable logic, validation, commands too complex to get right by language alone →
--with-scripts - Does it need reference docs? API guides, schemas, style guides, gotchas too long for SKILL.md →
--with-references - Does it depend on an MCP server or external tool?
If $ARGUMENTS already covers these, confirm and proceed.
CRITICAL — Scaffold before writing anything
NEVER write SKILL.md, scripts, or references manually before running scaffold.py.
scaffold.py generates correct frontmatter, folder structure, and placeholder files. Writing files first produces wrong frontmatter, breaks validation, and wastes time fixing structural issues.
If the target folder already exists: delete it first, then scaffold.
rm -rf <output>/<name>
uv run ${CLAUDE_SKILL_DIR}/scripts/scaffold.py --name <name> --output <output> ...
What ships with it
14 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.
- assets/skill-template.md 2.0 KB
- references/best-practices.md 5.8 KB
- references/description-optimization.md 5.1 KB
- references/evaluating-skills.md 4.9 KB
- references/patterns.md 5.5 KB
- references/scripts-guide.md 4.6 KB
- references/spec.md 3.3 KB
- scripts/autoevolve.py 18 KB runs code
- scripts/grade.py 14 KB runs code
- scripts/init-evals.py 7.3 KB runs code
- scripts/run-eval.py 10 KB runs code
- scripts/scaffold.py 10 KB runs code
- scripts/test-triggers.py 13 KB runs code
- scripts/validate.py 16 KB runs code
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.
- 11d ago First seen · 273 lines · 80 tokens per session scan C e754e2a02e81
skill-creator is a skill published in the GitHub repository damionrashford/media-os (18 stars, last pushed 3mo ago), licensed MIT. It adds 80 tokens to every session and 2,702 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
loudcheck
Loudness compliance verdicts against formal published standards — EBU R 128, ATSC A/85, or BS.1770 measure-only. Use it when audio or video has to pass a delivery gate: "is this file broadcast-legal?", "will this mix get rejected?", "how far off target is it and what's the exact fix?", batch-checking a delivery…
ideogram-ultra
Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control.
civitai
Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on Civitai, download it into ComfyUI, and use its trigger words. Optionally pair the official Civitai MCP for community features (images browsing, posting, collections).
chief-revenue-officer
Owns the revenue engine end to end: sales, monetization, pricing, customer success, retention, and partnerships. Use this for pricing and packaging decisions, sales strategy and coverage, forecast and pipeline health, churn and expansion, partner and channel strategy, or when marketing-sourced demand is not…
dev
One-command dev loop boot. Spins up portless (named HTTPS subdomain), emulate (stateful API mocks), the project's dev server, and an agent-browser session, all keyed to the current git branch. Use when starting a feature branch, switching worktrees, or returning to a project after a break. Skips silently with install…
storybook-mcp-integration
Reference for the Storybook MCP server itself (@storybook/addon-mcp): 6 tools across 3 toolsets (dev, docs, testing), availability detection, and per-agent toolset filtering. Use when setting up the server or calling these tools directly against components that already exist. For the end-to-end pipeline that turns a…