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/arctan303/creator.skill/gatewaynpx 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.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 | $0.00075 | $0.01207 |
| Opus 5 | $0.00037 | $0.00603 |
| Sonnet 5 | $0.00015 | $0.00241 |
| Haiku 4.5 | $0.00007 | $0.00121 |
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 4d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
工作流初始化技能
在当前工作空间部署 creator.skill 全套产品交付工作流。
核心原则
初始化是释放，不是创造。源文件来自预构建的释放包，不要在初始化过程中生成或修改 Skill 内容。
工作方式
- 确认用户意图：初始化工作流到当前工作空间。
- 检测当前宿主：优先按 gateway 技能自身安装位置判断——
SKILL.md位于~/.codex/skills/creator/→ Codex；位于~/.claude/skills/creator/→ Claude Code。无法定位自身时回退到~/.codex/、~/.claude/目录存在性；仍歧义时才询问用户。 - 确定源文件获取方式：
- 默认：从 GitHub Release 下载对应的释放包
- Codex → creator.codex.zip
- Claude Code → creator.claude.zip
- Release 地址：https://github.com/arctan303/creator.skill/releases/latest
- 备选：用户指定本地压缩包路径
- 默认：从 GitHub Release 下载对应的释放包
- 检查目标工作空间是否已有冲突文件。
- 两个平台共同检查：
.creator/Prompt 回归资产目录。 - Codex 检查：AGENTS.md、EVOLUTION.md、.version、.creator-manifest.json、.agents/skills/、.codex/evolution/signals.md
- Claude Code 检查：CLAUDE.md、EVOLUTION.md、.version、.creator-manifest.json、.claude/skills/、.claude/commands/、.claude/evolution/signals.md
- 检测到目标平台但工作空间已有另一平台产物（如目标为 Codex 却存在
.claude/）时，提示共存/覆盖，不静默双部署。 - 存在冲突时，询问用户处理方式。
- 两个平台共同检查：
- 解压释放包到当前工作空间根目录。
- 从释放包原样复制
.version与.creator-manifest.json到工作空间根目录；.version内容必须等于 manifest 的version字段。禁止写入安装日期或当前时间，版本一律以释放包内容为准。 - 验证关键文件已就位：
- 系统指令文件存在
.creator-manifest.json中列出的每个 Skill 目录均包含 SKILL.md，实际数量与skill_count一致- 对应 CLI 的 evolution/signals.md 已生成
.creator/tests/prompt-cases/cases.json与.creator/scripts/evaluate_prompt_cases.py已就位，并能完成静态 Prompt 契约评测.version与 manifest 中的版本一致
- 报告初始化结果：工作流版本、目标平台、技能数量、
.version与.creator-manifest.json位置、安装后验证结论、可用更新（如有）。
更新已有工作流
如果工作空间已有 .version 文件，展示当前版本并与释放包 manifest 比较，提示可用更新，由用户决定是否继续。
更新 = 整体替换工作流文件 + 保留运行时状态 + 冲突询问用户：
- 工作流文件（系统指令、EVOLUTION.md、技能目录、评测脚本、用例 README、
.version、.creator-manifest.json）直接用释放包整体替换；不自动回放或合并旧版本的自进化补丁——自进化历史保留在 signals.md 中，不随替换丢失。 evolution/signals.md是运行时台账，保留不清空；其中“已转补丁”条目若与新版本规则冲突，列出并询问用户，不静默应用或丢弃。.creator/tests/prompt-cases/cases.json按id合并；仅存在于任一侧的条目保留，同 ID 内容不同时列出冲突并让用户选择，禁止静默覆盖。- 其余任何冲突（文件内容不同、跨平台残留、补丁与新版规则冲突等）一律列出并询问用户，不自动选择。
- 替换后验证关键文件与版本一致，报告旧 → 新版本、保留 / 合并 / 询问项与验证结论。
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.
- 4d ago First seen · 65 lines · 75 tokens per session scan A 800838655d76
creator is a skill published in the GitHub repository arctan303/creator.skill (20 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 1,207 once invoked, about $0.0004 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
skill-forge
Generate a new skill from a simple prompt, then run an enhancer pass to tighten trigger rules, workflow, and output quality.
edgeone skill scanner
Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描…
avoid-ai-writing
Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice…
trulens-evaluation-workflow
Systematically evaluate your LLM application with TruLens.
agent-sop-author
Create (or update) and validate Agent SOPs (Standard Operating Procedures) - markdown-based workflows that guide AI agents through complex, multi-step tasks with RFC 2119 constraints.
omnisci
Run OmniScientist end to end in the OmniScientist CLI using DeepSeek V4 Flash. Turn raw research data (images, signals, audio, video, 3-D, tables, or graphs) and an open direction into perceived evidence, a falsifiable hypothesis, recorded analysis, real citations, a gated candidate paper, PDF, and Overleaf bundle.…