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 karashiiro/agent-skills --skill doing-creative-workgit clone --depth 1 https://github.com/karashiiro/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/karashiiro/agent-skills/doing-creative-work)<a href="https://agentmods.dev/skills/karashiiro/agent-skills/doing-creative-work"><img src="https://agentmods.dev/badge/skills/karashiiro/agent-skills/doing-creative-work/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/karashiiro/agent-skills/doing-creative-work"><img src="https://agentmods.dev/badge/skills/karashiiro/agent-skills/doing-creative-work.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 | $0.00014 | $0.00297 |
| Opus 5.5 | $0.00006 | $0.00119 |
| Sonnet 5.5 | $0.00003 | $0.00059 |
| Haiku 4.5 | $0.00001 | $0.00030 |
Grade A, and why
doing-creative-work 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 2mo 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.
What it actually says
Doing Creative Work
ALWAYS use metacog before beginning a creative task; feel the exact opposite of what you plan to build to avoid being generic and boring. Your initial creative instincts are often unrefined, and you can actually push them further by going in the opposite direction of what you'd think is the right approach.
Ask a subagent for advice to gauge your true, unfiltered design intention. If you don't do this, you'll trick yourself into thinking your "creative" idea is the subversion. You should strongly oppose the subagent's opinion. Then, feel the opposite and state how you plan to subvert it. Then, look for similarities between your "subverted" approach and your original one, and state how you plan to get away from that direction altogether.
Try mapping each idea to a trope and then evaluating if that trope is an obvious expectation or not. Do this exercise iteratively and explicitly until you arrive at something completely unlike your initial idea, and then explain your full reasoning, looking for gaps in it. The goal is not to rationalize or explain your original approach or to do it better; it's to change course entirely.
Don't forget to at least follow most of the conventions of the medium that are expected. There are rules about structure which should not be broken lightly, and choices within that structure which you are free to explore.
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.
- 2mo ago First seen · 15 lines · 14 tokens per session scan A 32aeeec20064
doing-creative-work is a skill published in the GitHub repository karashiiro/agent-skills (2 stars, last pushed 6mo ago), licensed Unlicense. It adds 14 tokens to every session and 297 once invoked, about $0.0001 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 2026-08-31.
doing-creative-work compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| doing-creative-workkarashiiro/agent-skills | Skill | 2 | 6mo ago | Unlicense | A | 14 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |