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 Zfinix/aster --skill refactor-safelygit clone --depth 1 https://github.com/Zfinix/asterWrote 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/zfinix/aster/refactor-safely)<a href="https://agentmods.dev/skills/zfinix/aster/refactor-safely"><img src="https://agentmods.dev/badge/skills/zfinix/aster/refactor-safely/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/zfinix/aster/refactor-safely"><img src="https://agentmods.dev/badge/skills/zfinix/aster/refactor-safely.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 | $0.00044 | $0.00324 |
| Opus 5.5 | $0.00018 | $0.00130 |
| Sonnet 5.5 | $0.00009 | $0.00065 |
| Haiku 4.5 | $0.00004 | $0.00032 |
Grade A, and why
refactor-safely 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 1mo 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
Refactor safely
- Map the blast radius first. Search every reference before changing one: the definition, call sites, tests, docs, config strings, serialization. A rename that misses a string reference compiles and then breaks at runtime.
- Green between every step. Refactor in compilable increments: move, check, rename, check. A ten-step refactor with one check at the end turns one mistake into an hour of archaeology.
- Never mix behavior change into a refactor. If you spot a bug mid refactor, note it, finish the neutral change, then fix the bug as its own change. Mixed diffs are unreviewable and unbisectable.
- Let the compiler drive mechanical renames. Change the definition first, then fix every error it reports; the error list is your checklist.
- Match the destination's conventions. Moved code adopts the naming, error handling, and comment density of the file it lands in.
- Prove neutrality at the end. The same tests that passed before must pass after, with no test edits beyond imports and paths. Any test that had to change semantically means it was not a refactor.
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.
- 1mo ago First seen · 25 lines · 44 tokens per session scan A 1a5c5ac38461
refactor-safely is a skill published in the GitHub repository Zfinix/aster (129 stars, last pushed 8d ago), licensed Apache-2.0. It adds 44 tokens to every session and 324 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
speccrew-dev-review-backend
SpecCrew Backend Code Review Skill. Reviews backend implementation code against system design documents, API contracts, and coding standards. Generates structured review reports with PASS/PARTIAL/FAIL verdict.
speccrew-dev-review-desktop
SpecCrew Desktop Code Review Skill. Reviews desktop app implementation code (Electron/Tauri) against system design documents and security standards. Generates structured review reports with PASS/PARTIAL/FAIL verdict.
speccrew-dev-review-frontend
SpecCrew Frontend Code Review Skill. Reviews web frontend implementation code against system design documents, API contracts, and coding standards. Generates structured review reports with PASS/PARTIAL/FAIL verdict.
speccrew-dev-review-mobile
SpecCrew Mobile Code Review Skill. Reviews mobile app implementation code against system design documents, API contracts, and platform-specific standards. Generates structured review reports with PASS/PARTIAL/FAIL verdict.
open-code-review
Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…