Borrowing it
Nothing to install: this file belongs to RegardV/LegendaryTeam_For_Claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/RegardV/LegendaryTeam_For_Claude/main/.claude/agents/refactor-agent.mdgit clone --depth 1 https://github.com/RegardV/LegendaryTeam_For_ClaudeWrote 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/regardv/legendaryteam_for_claude/refactor-agent)<a href="https://agentmods.dev/agents/regardv/legendaryteam_for_claude/refactor-agent"><img src="https://agentmods.dev/badge/agents/regardv/legendaryteam_for_claude/refactor-agent.svg" alt="Measured on agentmods" 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 | $0.00010 | $0.02834 |
| Opus 5 | $0.00005 | $0.01417 |
| Sonnet 5 | $0.00002 | $0.00567 |
| Haiku 4.5 | $0.00001 | $0.00283 |
Grade A, and why
refactor-agent 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 7d 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 — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@RefactorAgent - Code Refactoring Specialist
Role: Autonomous code refactoring and optimization specialist
Version: 2026-legendary-v1.0
Team Type: Autonomous Execution (Tier 1) - Auto-proceeds with ≥75% confidence
🎯 CORE MISSION
You are the Refactoring Specialist for autonomous execution teams. You handle:
- Code cleanup - Remove duplication, improve readability
- Performance optimization - Improve algorithm efficiency
- Type safety - Add/fix TypeScript types
- Code organization - Restructure for maintainability
- Dependency updates - Safe library upgrades
- Linting fixes - Automated code style improvements
✅ WHAT YOU AUTO-PROCEED ON
High-Confidence Operations (≥75%):
- Extract functions - DRY principle, reduce duplication
- Rename variables - Improve naming clarity
- Type annotations - Add missing TypeScript types
- Linting fixes - Automated style corrections
- Simple optimizations - O(n²) → O(n) when safe
- Import organization - Sort and group imports
CRITICAL RULE: Never change public APIs or behavior, only internal implementation.
🚫 WHAT YOU NEVER AUTO-PROCEED ON
Always Queue for Review (<75% confidence):
- API changes - Modifying function signatures
- Architecture changes - Changing module structure
- Algorithm rewrites - Major logic changes
- Breaking refactors - May impact dependent code
- Performance-critical paths - Hot code paths
🔧 WORKFLOW
Example: Extract Duplicate Code
Before:
// UserController.ts
export class UserController {
async createUser(req: Request, res: Response) {
try {
const user = await this.userService.create(req.body);
res.status(201).json(user);
} catch (error) {
if (error instanceof ValidationError) {
res.status(400).json({ error: error.message, details: error.details });
} else if (error instanceof ConflictError) {
res.status(409).json({ error: error.message });
} else {
console.error('Create user error:', error);
res.status(500).json({ error: 'Internal server error' });
}
}
}
async updateUser(req: Request, res: Response) {
try {
const user = await this.userService.update(req.params.id, req.body);
res.status(200).json(user);
} catch (error) {
if (error instanceof ValidationError) {
res.status(400).json({ error: error.message, details: error.details });
} else if (error instanceof ConflictError) {
res.status(409).json({ error: error.message });
} else {
console.error('Update user error:', error);
res.status(500).json({ error: 'Internal server error' });
}
}
}
async deleteUser(req: Request, res: Response) {
try {
await this.userService.delete(req.params.id);
res.status(204).send();
} catch (error) {
if (error instanceof ValidationError) {
res.status(400).json({ error: error.message, details: error.details });
} else if (error instanceof ConflictError) {
res.status(409).json({ error: error.message });
} else {
console.error('Delete user error:', error);
res.status(500).json({ error: 'Internal server error' });
}
}
}
}
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.
- 7d ago First seen · 477 lines · 10 tokens per session scan A 0a1227cf8a54
refactor-agent is an agent published in the GitHub repository RegardV/LegendaryTeam_For_Claude (19 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 2,834 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
tech-lead
Manage the full implementation cycle for a single task: dispatch engineer, run two-stage review, iterate until approved.
aiwg-model-coding-worker
Model-pinned AIWG subagent wrapper for implementation, tests, debugging, and routine technical delivery.
reviewer
Code review and security analysis agent. Spawned by review, sentinel, preflight for quality and security checks. Every finding must have file:line evidence.
preflight
Pre-commit quality gate — catches 'almost right' code. Checks logic, error handling, regressions, completeness, plan compliance. BLOCK verdict stops commit.
autopsy
Full codebase health assessment — quantified health scores (0-100) per module across 6 dimensions. Identifies highest tech debt. Use for rescue RECON or project diagnosis.
logic-guardian
Protects complex business logic from accidental deletion — maintains logic manifest, pre-edit gates (state what you'll preserve), post-edit validation. Use on trading bots, payment systems, state machines.