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/yeaight7/agent-powerups/safe-refactornpx skills add yeaight7/agent-powerups --skill safe-refactorgit clone --depth 1 https://github.com/yeaight7/agent-powerupsWrote 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/yeaight7/agent-powerups/safe-refactor)<a href="https://agentmods.dev/skills/yeaight7/agent-powerups/safe-refactor"><img src="https://agentmods.dev/badge/skills/yeaight7/agent-powerups/safe-refactor.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 | $0.00014 | $0.00400 |
| Opus 5 | $0.00007 | $0.00200 |
| Sonnet 5 | $0.00003 | $0.00080 |
| Haiku 4.5 | $0.00001 | $0.00040 |
Grade A, and why
safe-refactor 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.
What it actually says
Purpose
Restructure code in small, safe steps while preserving all externally observable behavior. Prevents refactor regressions where behavior silently changes.
When to Use
- Code needs structural improvement but its public API must remain unchanged.
- Naming, organization, or duplication needs cleanup after a feature is complete.
- Technical debt needs reduction without introducing risk.
Do not use this skill if there are no existing tests — write tests first.
Inputs
- Code to refactor.
- Existing test suite (required).
- Optional: specific goals (extract function, rename module, remove duplication).
Workflow
- Confirm behavior — Run the test suite. All tests must pass before starting.
- Plan — List the structural changes. Check each for API impact.
- Refactor in small steps — One change at a time, each independently reversible.
- Avoid interface changes — Do not alter public APIs, exported types, or CLI behavior unless explicitly intended.
- Validate after each step — Re-run targeted tests after each meaningful change.
Output
Changed:
- <structural change 1>
- <structural change 2>
Behavior unchanged because: <reasoning>
Validated by: <test commands run>
Verification
- Tests pass before starting
- Each step is small and independently reversible
- No unintended API or interface changes introduced
- Tests pass after each meaningful step
- Final test suite fully green
Failure Modes
- Missing tests — Stop. Write tests before refactoring. Behavior cannot be verified otherwise.
- Silent API change — If a refactor touches public interfaces, stop and confirm this is intentional.
- Bundled unrelated changes — Keep each step focused. Mixed changes make rollback and blame impossible.
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 · 57 lines · 14 tokens per session scan A 4be2e32a79fb
safe-refactor is a skill published in the GitHub repository yeaight7/agent-powerups (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 400 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
short-drama
制作多集 AI 微短剧：建立剧集圣经和角色参考，完成分集剧本、逐镜 I2V、对白审计、配音字幕 BGM 与成片，保持跨镜跨集一致性。 当用户说“AI/横屏/竖屏/微短剧、拍短剧、分集剧本、连续剧情视频、做几集短剧”时使用。 单条非剧情视频用 auto-short-video；只写单条脚本用 video-script；只生成一个视频片段用 ai-video-gen。.
clipify
从长视频中自动提取精彩片段，切成独立短视频，支持 16:9→9:16 竖版转制和逐字字幕烧录。 当用户说"视频切片""提取精彩片段""长视频切短""切成短视频""高光剪辑""逐字字幕""转竖版短视频"时使用。 和 video-highlights 的区别：clipify 专做英文口播找笑点+动态人脸 pan；video-highlights 更通用（中文/直播皆可），静态转竖版更稳。.
paper-explainer
科研论文解读：解析 arXiv/PDF 的公式与图表，提炼问题、贡献、方法、关键图和结论，再产出 B站/视频号解读视频或知乎/公众号图文。 当用户说“论文解读、讲论文、论文转视频/图文、科研科普、arXiv、学术视频”时使用。 本 SKILL 从论文做内容；video-to-article 从视频做图文，doc-convert 只转换文档格式。.
skill-wechat-publisher
微信公众号文章自动创作与发布工具。给定参考文章、文字或文档，自动搜索整理全网相关信息、生成图文并茂的公众号文章，并发布到微信公众号草稿箱。特别强调反 AI 检测写作。 触发场景（沾边就用）：用户提到"公众号 / 微信文章 / 推文 / 公号 / 发文 / mp / 草稿箱 / 群发"，或要求把话题/文档/笔记写成公众号文章并发布到微信。.
ecom-details-image
生成电商商品视觉方案：主图概念、场景图、详情页视觉方向和 AI 生图 Prompt。 当用户说"商品主图""详情页视觉""电商配图方案""商品场景图""带货视觉""产品视觉方向""详情页设计"时使用。 本 SKILL 出视觉方案+生图 Prompt（策划）；实际抠白底图用 remove-bg，实际生成图片用 ai-image-gen。.
multi-voice-dubbing
多角色对话配音：按 cast 和逐行对白为不同角色分配音色与情绪，合成多声线音轨和带角色名字幕。 当用户说“多角色/双人/剧本/对话配音、多人对白、不同角色不同声音、有声剧配音”时使用。 单一公共音色用 tts-voiceover；克隆本人音色用 voice-clone；整部短剧制作由 short-drama 编排。.