Borrowing it
Nothing to install: this file belongs to rakovi4/continue-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rakovi4/continue-framework/main/.claude/skills/refactor/SKILL.mdgit clone --depth 1 https://github.com/rakovi4/continue-frameworkWrote 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/rakovi4/continue-framework/refactor)<a href="https://agentmods.dev/skills/rakovi4/continue-framework/refactor"><img src="https://agentmods.dev/badge/skills/rakovi4/continue-framework/refactor/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/rakovi4/continue-framework/refactor"><img src="https://agentmods.dev/badge/skills/rakovi4/continue-framework/refactor.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 | $0.00027 | $0.01176 |
| Opus 5.5 | $0.00011 | $0.00470 |
| Sonnet 5.5 | $0.00005 | $0.00235 |
| Haiku 4.5 | $0.00003 | $0.00118 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/refactor
Dispatch one independent refactor-agent per coherent scope. The worker applies
all applicable refactoring checks; scope partitioning controls parallelism, not
checklist coverage. Load .claude/templates/workflow/quality-execution.md for
ownership, scheduling, evidence reuse, inspection modes, and result joining.
Usage
/refactor— analyze and refactor the current scope/refactor {Target}— analyze and refactor a named target
Dispatch
- Resolve the target, tests, helpers, and relevant collaborators. Load shared
coding detail, frontend rules where relevant, and active technology bindings.
Map responsibilities using
.claude/templates/refactoring/scan-checklist.md. - Dispatch
refactor-agentwith the scope manifest, input revisions, applicable context, and execution mode. The worker must be independent of the primary implementation/test author and load every applicable M, D, and T check. It must not nest fan-outs. For large scopes, partition by cohesive capability, assign each partition all applicable clusters, and name an owner for cross-capability checks. Shared writes have one owner. Partitioned dispatches are read-only initially; gather every partition and cross-capability result before granting fixes. - Default unpartitioned standalone/task mode is scan-and-fix: scan the complete scope,
resolve findings one refactoring at a time, verify, and return the completed
result using
refactor-agent.md. A small scope uses this same route. - Stage 2 may dispatch inspect on the stable joined candidate alongside coverage. It returns findings without edits; this is not a completed gate. After coverage-driven changes are verified and behavior is published, the coordinator explicitly dispatches fix, granting owned paths and passing current revisions and invalidations. Reuse the inspector when available; otherwise pass its evidence to a new independent worker. Revalidate affected checks, apply fixes, and await verification before completing the gate.
- A worker retained from
/test-reviewmay run/refactoronly after the coordinator publishes the reviewed tests and explicitly dispatches this skill. Keep the two named phases and results distinct; never auto-run the next phase. GREEN scope reuse followsquality-execution.md; every file and check remains accounted for, including cross-file effects.
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 Changed · +6 lines e4b6a368617a
- 1mo ago Changed 626b8a2fe8ce
- 2mo ago First seen · 85 lines · 27 tokens per session scan A d20b84066199
refactor is a skill published in the GitHub repository rakovi4/continue-framework (54 stars, last pushed 29d ago), licensed MIT. It adds 27 tokens to every session and 1,176 once invoked, about $0.0001 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…