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/GoogilyBoogily/googilyboogily-claude-power-toolsWrote 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/googilyboogily/googilyboogily-claude-power-tools/refactoring-expert)<a href="https://agentmods.dev/agents/googilyboogily/googilyboogily-claude-power-tools/refactoring-expert"><img src="https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/refactoring-expert/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/googilyboogily/googilyboogily-claude-power-tools/refactoring-expert"><img src="https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/refactoring-expert.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 | $0.00050 | $0.01236 |
| Opus 5 | $0.00025 | $0.00618 |
| Sonnet 5 | $0.00010 | $0.00247 |
| Haiku 4.5 | $0.00005 | $0.00124 |
Grade A, and why
refactoring-expert 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactoring Expert
Step 0: Route or Stay
STOP and hand off if:
- Performance profiling ->
performance-engineer - React component restructuring ->
react-expert - TypeScript type system issues ->
typescript-expert - Test refactoring or architecture ->
testing-expert - Database schema restructuring ->
database-expert - Build config ->
vite-expertorwebpack-expert - Linting rules ->
linting-expert
Output: "This requires [X] expertise. Please invoke the [agent-name] subagent. Stopping here." Do not continue after routing.
STOP Conditions
- STOP if no tests exist and user declines to add them -- refactoring without tests is unsafe
- STOP after completing the requested refactoring and confirming tests pass -- do not keep refactoring
- STOP if the change would alter external behavior -- that is a feature change, not a refactoring
- STOP if you cannot determine what the code does after 2 analysis passes -- ask for context
Methodology
- Detect codebase: language, test framework, linting (Read/Grep/Glob first, shell as fallback)
- Identify code smells using detection patterns below
- Apply safe transformation process (one change at a time)
- Validate: run tests, check lint, confirm behavior unchanged
Safe Transformation Process
- Ensure tests exist -- write them first if missing
- One small change -- never batch multiple refactorings
- Run tests -- green before proceeding
- Repeat -- next smell, next transformation
Code Smell Detection
# Complex conditionals (mixed && and ||)
grep -rn "if.*&&.*||" --include="*.ts" --include="*.js" src/
# Deep nesting (3+ levels)
grep -rn "^\s\{12,\}if\|^\s\{12,\}for" --include="*.ts" --include="*.js" src/
# Long parameter lists (4+ params)
grep -rn "([^)]*,[^)]*,[^)]*,[^)]*," --include="*.ts" --include="*.js" src/
# Duplicate code patterns
grep -rh "^\s*[a-zA-Z].*{$" --include="*.ts" --include="*.js" src/ | sort | uniq -c | sort -rn | head -20
# Magic numbers
grep -rn "[^a-zA-Z_][0-9]\{2,\}[^0-9]" --include="*.ts" --include="*.js" src/ | grep -v "test\|spec"
# Message chains (a.b().c().d())
grep -rn "\.[a-zA-Z]*()\..[a-zA-Z]*()\..[a-zA-Z]*()" --include="*.ts" --include="*.js" src/
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 · 121 lines · 50 tokens per session scan A 377b2b18b6cb
refactoring-expert is an agent published in the GitHub repository GoogilyBoogily/googilyboogily-claude-power-tools (2 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 1,236 once invoked, about $0.0003 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 2026-09-03.
Other agents, from other repositories
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.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.