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 fco3lho/unlazier-ai --skill refactoringgit clone --depth 1 https://github.com/fco3lho/unlazier-aiWrote 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/fco3lho/unlazier-ai/refactoring)<a href="https://agentmods.dev/skills/fco3lho/unlazier-ai/refactoring"><img src="https://agentmods.dev/badge/skills/fco3lho/unlazier-ai/refactoring/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/fco3lho/unlazier-ai/refactoring"><img src="https://agentmods.dev/badge/skills/fco3lho/unlazier-ai/refactoring.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 | $0.00037 | $0.00287 |
| Opus 5 | $0.00018 | $0.00143 |
| Sonnet 5 | $0.00007 | $0.00057 |
| Haiku 4.5 | $0.00004 | $0.00029 |
Grade A, and why
refactoring 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 10d 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
Refactoring Workflow
Before Starting
- Identify the exact scope of the refactoring. What specific improvement is asked?
- If the request is vague ("clean this up"), ask for specifics before starting.
Rules
Surgical Changes
- Refactor only what was requested. Do not improve adjacent code.
- Match existing style, even if you personally prefer a different one.
- If you discover unrelated dead code, mention it — don't delete it.
- Remove imports/variables/functions YOUR changes made unused. Not pre-existing ones.
Simplicity First
- Prefer the simplest structure that solves the problem.
- Extract functions only when they are reused or reduce cognitive load.
- Do not introduce abstractions "for future flexibility."
- A 50-line flat function is often better than 5 classes with inheritance.
Verification
- Tests pass before and after (run the full suite)
- Diff shows only the intended lines changed
- No new TODOs, FIXMEs, or stubs introduced
After Refactoring
Run git diff and check:
- Every changed line traces to the original request?
- No unrelated formatting, style, or comment changes?
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.
- 10d ago First seen · 40 lines · 37 tokens per session scan A 0bf86046b84b
refactoring is a skill published in the GitHub repository fco3lho/unlazier-ai (3 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 287 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
oh-my-openagent
Use when configuring OpenCode for multi-model orchestration, Agent Harness patterns, CI/automation integration, or token cost optimization. Oh-My-OpenAgent: curated OpenCode agent configurations and prompt engineering patterns.
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
at-vision
Inspect screenshots, photos, diagrams, image paths, and image URLs when the task depends on visible content. Use when the prompt lacks actual image content, native inspection fails, or the user requests inspectimage; prefer the MCP tool, then the installed CLI.
openspec-bulk-apply-change
Use when multiple active OpenSpec changes should be applied concurrently in isolated worktrees with delegated verification and no merge.
feedback
Collect and submit feedback about Superset (bug reports, feature requests, or general feedback) privately to the Superset team or as a public GitHub issue. Use when the user wants to report a Superset bug, request a feature, or send feedback about Superset.
ci-triage
Diagnose a failing GitHub Actions run — find the first real error in the logs, tell a flake apart from a genuine failure, and identify the commit that broke it. Use when checks are red on a PR, a workflow failed, the build is broken, CI is flaky, or the user asks why a run failed or whether a failure is real.