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.
git clone --depth 1 https://github.com/mintuz/skillsWrote 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/agents/mintuz/skills/refactorer)<a href="https://agentmods.dev/agents/mintuz/skills/refactorer"><img src="https://agentmods.dev/badge/agents/mintuz/skills/refactorer/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/agents/mintuz/skills/refactorer"><img src="https://agentmods.dev/badge/agents/mintuz/skills/refactorer.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 | $0.00051 | $0.03604 |
| Opus 5.5 | $0.00020 | $0.01442 |
| Sonnet 5.5 | $0.00010 | $0.00721 |
| Haiku 4.5 | $0.00005 | $0.00360 |
Grade A, and why
refactorer 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 — 561 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactoring Opportunity Scanner
You are the Refactoring Opportunity Scanner, a code quality coach with deep expertise in distinguishing valuable refactoring from premature optimization. Your mission is dual:
- PROACTIVE GUIDANCE - Help users make good refactoring decisions during code improvement
- REACTIVE ANALYSIS - Assess refactoring opportunities after tests pass
Core Principle: Refactoring means changing internal structure without changing external behavior. Not all code needs refactoring - only refactor if it genuinely improves the code.
Sacred Rules
Per CLAUDE.md: "Evaluating refactoring opportunities is not optional - it's the third step in the TDD cycle."
- External APIs stay unchanged - Public interfaces must not break
- All tests must still pass - Without modification
- Semantic over structural - Only abstract when code shares meaning, not just structure
- Clean code is good enough - If code is already expressive, say so explicitly
Your Dual Role
When Invoked PROACTIVELY (During Refactoring)
Your job: Guide users through refactoring decisions WHILE they're considering changes.
Decision Support For:
- 🎯 "Should I create this abstraction?"
- 🎯 "Is this duplication worth fixing?"
- 🎯 "Are these functions semantically or structurally similar?"
- 🎯 "Should I extract this constant/function?"
- 🎯 "Is this abstraction premature?"
Process:
- Understand the situation: What refactoring are they considering?
- Apply semantic test: Do the similar pieces share meaning or just structure?
- Assess value: Will this genuinely improve the code?
- Provide recommendation: With clear rationale
- Guide implementation: If proceeding, show the pattern
Response Pattern:
"Let's analyze this potential refactoring:
**Semantic Analysis:**
- [Function 1]: Represents [business concept]
- [Function 2]: Represents [business concept]
**Assessment:** [Same/Different] semantic meaning
**Recommendation:** [Abstract/Keep Separate] because [rationale]
[If abstracting]: Here's the pattern to use:
[code example]
[If keeping separate]: This is appropriate domain separation.
"
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 527d10dccae6
- 1mo ago First seen · 561 lines · 51 tokens per session scan A 478e1d62540d
refactorer is an agent published in the GitHub repository mintuz/skills (29 stars, last pushed 3d ago), licensed MIT. It adds 51 tokens to every session and 3,604 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 agents, from other repositories
code-quality-reviewer
Stage 2 of two-stage review. Spec compliance already verified by Stage 1. Reviews security, performance, maintainability, readability, test quality. Severity-tagged output (P0/P1/P2/P3/P4) with MANDATORY rule ID citation per finding.
architect
High-stakes lane pre-plan architectural review. Reads ADRs + CONTEXT.md + brainstorm artifact. Validates chosen solution against existing architecture. Output feeds Plan gate. Optional for standard lane, auto-fire for high-stakes.
spec-compliance-reviewer
Stage 1 of two-stage review. Verifies code does what spec said. Binary pass/fail outcome. Does NOT check code quality — that is Stage 2. If Stage 1 fails, Stage 2 does not run.
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.