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 rjroy/vibe-garden --skill refactorgit clone --depth 1 https://github.com/rjroy/vibe-gardenWrote 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/rjroy/vibe-garden/refactor)<a href="https://agentmods.dev/skills/rjroy/vibe-garden/refactor"><img src="https://agentmods.dev/badge/skills/rjroy/vibe-garden/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/rjroy/vibe-garden/refactor"><img src="https://agentmods.dev/badge/skills/rjroy/vibe-garden/refactor.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00038 | $0.00527 |
| Opus 5.5 | $0.00015 | $0.00211 |
| Sonnet 5.5 | $0.00008 | $0.00105 |
| Haiku 4.5 | $0.00004 | $0.00053 |
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 9d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactor
Begin with read-only diagnosis. The goal is to help the user decide whether a concrete refactoring is worth doing, not to produce a checklist or change code.
Scope and investigation
Establish the area or upcoming change from the user's request and conversation. If it is unclear, ask one bounded question before exploring. Do not infer a large scope from Git state or sweep the repository by default.
Inspect the relevant implementation, tests, callers, and consumers to understand what the code does and where maintenance friction occurs. Use code search, exploration, or a suitable review agent in proportion to the scope. Treat old plans, designs, and other work artifacts as context only; current user intent governs.
Use Fowler's code-smell vocabulary as a set of diagnostic cues, not a required catalog to complete. For example, duplication can cause fixes to diverge; shotgun surgery can make one change touch many places; speculative generality can impose abstraction costs without a demonstrated need; lazy elements, middle men, data clumps, and primitive obsession can obscure responsibilities or concepts. Long methods, feature envy, message chains, global or mutable state, and other familiar smells may also be relevant. A loop, switch, data class, comment, or simple name is not inherently a defect. Consider conflicting cues and the actual design context rather than treating any pattern as proof.
Findings and user choice
Report only findings supported by concrete file and code evidence. Explain the actual maintenance or future-change cost, then offer a bounded, behavior-preserving correction option. Ordinary naming or formatting concerns are not findings unless they cause meaningful cost. No finding is a valid result; do not invent work to fill a quota.
Present findings to the user and let them choose whether, and which, to address.
Do not edit files, apply fixes, or begin implementation during this diagnosis.
If the user asks to proceed, hand /simplify only the selected findings and
compact scope: affected files/surface, evidence, behavior to preserve, and any
explicitly accepted change. Do not create a spec, matrix, or approval document.
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.
- 9d ago First seen · 50 lines · 38 tokens per session scan A 2ffd6e53dc9f
refactor is a skill published in the GitHub repository rjroy/vibe-garden (6 stars, last pushed 10d ago), licensed MIT. It adds 38 tokens to every session and 527 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 2026-10-08.
Other skills, from other repositories
review
Dispatched after a task lands at inreview to produce a structured CTO-grade verdict on the work and its PR. Two invocation paths: composer Phase 4 (orchestrator dispatches after the implementer's inreview write, surfaces the verdict to HOTL, stops), and direct mode from the piyaz skill on requests ("review VF-N"…
critical-code-reviewer
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
genshijin-review
A compact pull-request review format that writes one actionable finding per line in Japanese or English.
triage
Triages a PR comment — from a bot (Copilot, CI) or a human reviewer. Routes to the triagehelper.py helper for identity checks, thread snapshotting, isolated-worktree fixes, and publish/reply/resolve mechanics; you classify the finding and apply a justified fix. --dry-run is fully read-only (investigation and a printed…
pr-review
Comprehensive PR review across six dimensions — cost impact, environment drift, ownership gaps, SOC 2 compliance, deprecated API / version hygiene, and rollback feasibility. Each mode inspects the diff and current file state, reports findings with severity, and recommends concrete fixes. Use when preparing a PR for…