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 arctan303/creator.skill --skill gatewaygit clone --depth 1 https://github.com/arctan303/creator.skillWrote 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/arctan303/creator.skill/gateway)<a href="https://agentmods.dev/skills/arctan303/creator.skill/gateway"><img src="https://agentmods.dev/badge/skills/arctan303/creator.skill/gateway/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/arctan303/creator.skill/gateway"><img src="https://agentmods.dev/badge/skills/arctan303/creator.skill/gateway.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00045 | $0.00948 |
| Opus 5.5 | $0.00018 | $0.00379 |
| Sonnet 5.5 | $0.00009 | $0.00190 |
| Haiku 4.5 | $0.00005 | $0.00095 |
Grade A, and why
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 7d 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install creator.skill / 安装 creator.skill
Install the prepared package; do not generate another policy tree. Both hosts use creator-workflow.zip, canonical AGENTS.md and .agents/skills/. Claude discovery uses thin .claude/skills/ adapters. No CLAUDE.md or legacy slash commands are generated.
安装预构建包，不重新生成规则。两宿主共享一个包、一份 AGENTS.md 和一套技能正文；Claude 只增加发现入口。
Workflow / 工作步骤
- Establish the exact target project and authorized scope. Existing permission to upgrade covers the normal dry-run and conflict-free apply; do not ask again. Installing the workflow does not authorize migrating project docs, changing a user-level gateway, or upgrading other repositories.
- Obtain
creator-workflow.zipfrom the user's selected local build or the trusted official release. Inspect release version and artifact names first; do not claim an unreleased version is available. Hashes detect content changes but do not authenticate an untrusted publisher. - Read host compatibility and commands. Use the bundled
scripts/install_workflow.pywith an explicit--rootand--package. The default is a read-only JSON plan. Do not manually extract the workflow ZIP over the project. - For a pre-1.6 installation, supply the matching trusted old official ZIP with
--baseline-package; repeat for both old host packages if needed. A filename or.versionalone does not prove ownership. Unknown or modified files remain intact and appear as conflicts. There is no force-overwrite option. - When the plan is conflict-free and within the user's authorized scope, rerun with
--apply. A conflict blocks all installation writes. For an interrupted transaction inspect--recover, then use--recover --applywithin the installation authorization. Recovery will not overwrite concurrent edits. Keep the journal when manual reconciliation is necessary. - Validate installed version, manifests and canonical files, then run the packaged structural evaluator. Diagnose Claude discovery separately: known host version, local/ancestor CLAUDE files, settings and
/context. File installation does not prove live host discovery or model behavior. - Report package/version, preserved/merged/removed paths, unresolved conflicts and compatibility evidence. Report docs migration state separately; never create
completemerely because installation succeeded. If docs adaptation was authorized, continue with the migration guide.
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.
- 7d ago Changed · -38 lines · -30 tokens per session b1bdc7b114c5
- 1mo ago Changed · +4 lines 98155223c64e
- 1mo ago First seen · 65 lines · 75 tokens per session scan A 800838655d76
creator is a skill published in the GitHub repository arctan303/creator.skill (19 stars, last pushed 7d ago), licensed MIT. It adds 45 tokens to every session and 948 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
development
An index of programming guidance for Python, Go, Rust, TypeScript, Java, C++, and shell scripting.
tencent-docs
A Tencent Docs assistant for creating, reading, editing, organizing, importing, and exporting online documents, spreadsheets, presentations, diagrams, and forms.
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error. Also load when a live run you started for the user fails with an error from…
wechat-search
Search WeChat Official Account articles using OpenClaw's web search, Tavily API, and web fetch capabilities with compliance-focused design.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.