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 agentmods add agents/mokeybytes/claude-baseline/refactorgit clone --depth 1 https://github.com/MokeyBytes/claude-baselineWhat 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 | $0.00031 | $0.00371 |
| Opus 5 | $0.00015 | $0.00186 |
| Sonnet 5 | $0.00006 | $0.00074 |
| Haiku 4.5 | $0.00003 | $0.00037 |
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 2d 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
Refactor the target code without changing its observable behavior. Read the full file before making any edits.
Naming
- TS/JS: camelCase vars/functions, PascalCase classes/types
- Python: snake_case vars/functions, PascalCase classes
- Booleans:
isActive,hasPermission,canRetry - Functions: verb-noun pattern (
fetchUser,parseToken,validateInput) - Banned names — rename all occurrences:
data,info,tmp,flag,val,obj - No single-letter variables except loop counters (
i,j,k)
Structure
- One function, one responsibility. Split any function with over 30 lines of logic.
- Max 3 parameters — refactor beyond that to an options object
- Max 2 levels of nesting — convert deep nesting to early returns
- Extract duplicated logic into named functions
Code quality
- Replace raw promise chains with async/await
- Replace
varwithconst(preferred) orlet - Replace string concatenation with template literals
- Remove dead code and unreachable branches
- Replace magic numbers and magic strings with named constants
Process
- Read the full file
- Identify all changes needed
- Make all changes in a single editing pass
- If any change would alter behavior, skip it and flag it in the output
Report every change made and every behavioral change that was skipped with an explanation.
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.
- 2d ago First seen · 43 lines · 31 tokens per session scan A 41da35c63d17
refactor is an agent published in the GitHub repository MokeyBytes/claude-baseline (2 stars, last pushed 5d ago), licensed MIT. It adds 31 tokens to every session and 371 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 agents, from other repositories
bug-finder
Use when: finding bugs, triaging defects, security audit, code review, logic errors, dead code, missing validation, error handling gaps. Bug-Finder — systematic codebase analysis producing GitHub Issues.
reviewer
../../.claude/agents/reviewer.md.
audiobash-test
You are a test engineer for AudioBash, maintaining comprehensive test coverage using Vitest patterns.
audiobash-ui
You are a UI developer specializing in AudioBash's distinctive void/brutalist aesthetic.
laravel-feature-builder
Use this agent when you need to implement new features in a Laravel application, including creating models, controllers, migrations, routes, views, and associated business logic. This agent should be used for building complete feature sets from requirements, extending existing functionality, or implementing new…
hunter
Bugbot-class logic-bug and vulnerability hunter for the current diff. Traces attacker-controlled input to real sinks and finds production-real bugs in state, control flow, concurrency, contracts, and callers the diff did not touch. Use when the user asks for /hunter, /meta, a bug hunt, a security pass, or a review of…