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/supersynergy/awesome-agentic-coding/refactornpx skills add Supersynergy/awesome-agentic-coding --skill refactorgit clone --depth 1 https://github.com/Supersynergy/awesome-agentic-codingWhat 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 | $0.00013 | $0.00279 |
| Opus 5 | $0.00006 | $0.00139 |
| Sonnet 5 | $0.00003 | $0.00056 |
| Haiku 4.5 | $0.00001 | $0.00028 |
Grade A, and why
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 2d 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
Safe Refactoring Protocol
Target: $ARGUMENTS
Step 1: Baseline
- Run tests first. If they fail, stop — fix tests before refactoring.
- Note current test count and pass rate.
Step 2: Plan
List every change you will make. Group into atomic steps where:
- Each step leaves the code in a working state
- Each step can be verified independently
- Steps are ordered by dependency
Step 3: Execute (one step at a time)
For each step:
- Make the change
- Run tests
- If tests pass: continue to next step
- If tests fail: undo this step and investigate
Step 4: Final Verification
- Run full test suite
- Compare test count (should be same or higher, never lower)
- Run linter if available
Rules
- Never change behavior. Only structure.
- Never delete tests. Never skip tests.
- If a refactoring step breaks tests, it means the refactoring is wrong, not the test.
- Keep the diff minimal. Don't rename things "while you're at it."
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.
- 2d ago First seen · 39 lines · 13 tokens per session scan A 37f85e59d156
refactor is a skill published in the GitHub repository Supersynergy/awesome-agentic-coding (1 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 279 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
aiwiki-research-refresh-privacy
定期为 AiWiki「LLM 隐私保护」主题做一次「高质量一手来源研究 → 去重 → 三道硬闸门把关 → 走隐私条目流水线 → 过闸门」的扩充。当需要发现并新增 LLM 隐私攻防新选题（尤其由月度定时触发器拉起的无人值守会话），且要保证一手出处、不与现有条目重复、不制造假安全时使用。.
aiwiki-privacy-entry-author
为 AiWiki「LLM 隐私保护」主题撰写或修订一条攻防条目（privacy/ 下的 .mdx）。当需要新增/改写隐私条目、并保证第一人称红线、九节结构、三道硬闸门、隐私 frontmatter 与一手出处时使用。.
aiwiki-research-refresh
定期为 AiWiki 做一次「高质量来源研究 → 去重 → 质量把关 → 走条目流水线 → 过闸门」的扩充。当需要发现并新增「AI 使用误区」新选题（尤其由月度定时触发器拉起的无人值守会话），且要保证来源质量、不与现有条目重复时使用。.
aiwiki-entry-author
为 AiWiki 撰写或修订一条「误区」条目（docs/ 下的 .mdx）。当需要新增/改写误区条目、并保证第一人称 AI 声音、七段结构、frontmatter 规范与可核查出处时使用。.
aiwiki-translator
把一条 AiWiki 中文误区条目（docs/ 下的 .mdx）翻译成英文镜像，输出到 i18n/en/ 对应路径。当需要为新增或修订的中文条目生成/更新英文版时使用。.
issue-triage
Issue triage: audit open issues, categorize, detect duplicates, cross-ref PRs, risk assessment, post comments. Args: "all" for deep analysis of all, issue numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French.