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 Sistema2D/FrameCode-VibeWork --skill code-hygiene-refactorgit clone --depth 1 https://github.com/Sistema2D/FrameCode-VibeWorkWrote 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/sistema2d/framecode-vibework/code-hygiene-refactor)<a href="https://agentmods.dev/skills/sistema2d/framecode-vibework/code-hygiene-refactor"><img src="https://agentmods.dev/badge/skills/sistema2d/framecode-vibework/code-hygiene-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/sistema2d/framecode-vibework/code-hygiene-refactor"><img src="https://agentmods.dev/badge/skills/sistema2d/framecode-vibework/code-hygiene-refactor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 123 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00051 | $0.01270 |
| Opus 5.5 | $0.00020 | $0.00508 |
| Sonnet 5.5 | $0.00010 | $0.00254 |
| Haiku 4.5 | $0.00005 | $0.00127 |
Grade A, and why
code-hygiene-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 18d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Code Hygiene Refactor
Purpose
Drive active cleanup of duplication, stale files, unnecessary code, oversized modules, and retroactive technical debt while preserving behavior. This skill is a Markdown-only operational tool: it tells the agent what to inspect, what to block, and what evidence to record.
Activation Triggers
Load this skill when:
- a user reports duplication, monoliths, repeated snippets, stale files, unnecessary files, dead code, technical debt, cleanup, or the Portuguese equivalents: higiene de código, limpeza, duplicação, código duplicado, arquivo obsoleto, arquivo morto, código morto, refatoração, dívida técnica, monolito, or sobras de implementação;
- retroactive instantiation is applied to an existing project;
- a file is large, low-cohesion, or repeatedly changed;
- a plan touches code with known
#tech-debt; - an agent is tempted to copy/paste similar code;
- a cleanup/refactoring plan is opened.
Inputs
Active plan and scope, changed-path and ownership evidence, similar-code search, dependency/consumer references, focused behavior checks, and rollback or restoration source for removals.
Non-Negotiable Rules
- Preserve observable behavior unless a separate functional plan exists.
- Do not remove dead code without evidence from search, tests, owners, routes, or build behavior.
- Do not combine broad cleanup with a feature delivery unless the cleanup is required to keep the feature small.
- Do not introduce new dependencies for cleanup without explicit research and plan approval.
- Prefer extracting existing repeated logic over inventing generic abstractions.
- Keep each cleanup batch reviewable and reversible.
Proportionality Check
Before creating a utility, service, wrapper, component, dependency, file, layer, or parallel mechanism, evaluate in order:
- Is the behavior necessary in the current scope?
- Does the codebase already contain a complete or partial solution?
- Does the language, framework, platform, or infrastructure provide a native capability?
- Does an already installed dependency solve it adequately?
- Only then, is new code justified?
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.
- 18d ago Changed · -5 lines · +31 tokens per session 73c6e279fb9f
- 1mo ago Changed · +11 lines a058b586a9ed
- 1mo ago First seen · 125 lines · 20 tokens per session scan A e248205685d4
code-hygiene-refactor is a skill published in the GitHub repository Sistema2D/FrameCode-VibeWork (29 stars, last pushed 16d ago), licensed Apache-2.0. It adds 51 tokens to every session and 1,270 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
sdlc-cross-review
Use when a change needs an independent review — acting as the reviewer in a fresh context, or preparing the diff and criteria for a reviewer in another session, model or tool. Enforces reviewer independence (not the author's context, not the author's operator), checks data classes before any content leaves for a…
ork-verify
Verify that existing work is ready to merge, release, or hand off using an explicit evidence contract. Use when a request asks to verify, validate, prove, check readiness, run the relevant tests, or distinguish a claimed result from an observed one. Do not use to write missing tests or fix failures.
ork-assess
Assess a code change, design, architecture, workflow, or competing options against explicit criteria and evidence. Use when a request asks to assess, rate, compare, identify trade-offs, evaluate readiness, or decide whether an approach is good enough. Do not use for a full pull-request review or to implement a chosen…
crap-analyzer
Use to produce a risk-based refactor + test plan for recently-changed code on a diff/branch/PR by computing CRAP (complexity × untested) on changed methods. Multi-language — TypeScript, JavaScript, Python, Java, Kotlin, Go, Ruby, C#, Rust, PHP — auto-discovers how the repo generates coverage. Triggers …
review-thread
Record review verdicts and run the StateNote review thread on an agent-operation instance — every ReviewRequest verdict is one atomic batch-direct-write that advances status and co-writes a reviewnote explaining why, and findings are corrected by appending notes rather than editing them.
skill-scope-control
Analisa se alterações, diffs e PRs continuam alinhados ao objetivo declarado, identificando escopo extra e propondo manter, separar ou justificar.