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/rakovi4/continue-framework/refactornpx skills add rakovi4/continue-framework --skill refactorgit clone --depth 1 https://github.com/rakovi4/continue-frameworkWhat 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 | $0.00027 | $0.01051 |
| Opus 5 | $0.00014 | $0.00526 |
| Sonnet 5 | $0.00005 | $0.00210 |
| Haiku 4.5 | $0.00003 | $0.00105 |
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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/refactor
Scatter–gather: three parallel read-only detectors scan for smells, then a single serial fixer applies refactorings one at a time. Detectors never edit — only the fixer writes, and it re-scans cascades after each change, so the "one refactoring at a time" invariant is preserved.
Usage
/refactor # Analyze current code for smells
/refactor Email # Create Email value object
/refactor UserService # Refactor specific file
Workflow
- Identify the target file (and its tests / siblings). This determines which
file-type checks apply (backend vs
.tsx). - Dispatch the detectors concurrently and await all of them — start every
named agent before awaiting results, then gather every result. No dispatch is
detached or fire-and-forget: step 3 requires the complete result set.
Each runs only its cluster of
.claude/templates/refactoring/scan-checklist.mdand returns a candidate table:refactor-mechanics-agent— cluster M (size, complexity, variables, dead code)refactor-design-agent— cluster D (domain modeling, behavior placement, type safety)refactor-duplication-agent— cluster T (sibling/cross-class duplication, tests, frontend)
- Gather + fix: hand all candidate tables to
.claude/agents/refactor-agent.md(the serial fixer). It merges, dedups, orders highest-impact-first, applies ONE refactoring at a time (loading the template from the Code Smells Routing Table), runs tests, and re-scans cascades inline — repeating until clean.
Small-file shortcut
If the target is small with few methods/concerns, skip the fan-out and run a
single refactor-agent pass over the whole checklist — the detector
orchestration + merge overhead can exceed the single-agent cost on tiny files.
Dispatch that lone pass and await its result. Here the fixer's report is this
skill's entire output, so an unawaited call could report "refactored" before a
file was touched.
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 · 85 lines · 27 tokens per session scan A d20b84066199
refactor is a skill published in the GitHub repository rakovi4/continue-framework (50 stars, last pushed 5d ago), licensed MIT. It adds 27 tokens to every session and 1,051 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…