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 oyi77/1ai-skills --skill refactor-agentgit clone --depth 1 https://github.com/oyi77/1ai-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/skills/oyi77/1ai-skills/refactor-agent)<a href="https://agentmods.dev/skills/oyi77/1ai-skills/refactor-agent"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/refactor-agent/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/oyi77/1ai-skills/refactor-agent"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/refactor-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00022 | $0.01148 |
| Opus 5 | $0.00011 | $0.00574 |
| Sonnet 5 | $0.00004 | $0.00230 |
| Haiku 4.5 | $0.00002 | $0.00115 |
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 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactor Agent
Quick Reference — see parent for full agent ecosystem.
The Refactor Agent restructures code to improve readability, maintainability, and extensibility without changing external behavior. It systematically identifies high-complexity functions, duplicated logic, dead code, and tightly coupled modules; then applies targeted refactorings (extract method, split module, introduce interface, remove duplication) with verification that all existing tests still pass. Its mantra: make the change easy, then make the easy change.
When Not to Use
- Simple or one-off tasks — if the task is straightforward, direct execution is faster than structured methodology.
- Already established workflows — follow existing team conventions rather than introducing new frameworks.
- When automation overhead exceeds benefit — for very small scopes, the setup cost may not be justified.
Dependencies
- Python 3.8+ or Node.js 18+
- Access to relevant APIs/services for your specific use case
- Basic understanding of the domain concepts
Commands
# Refer to the skill's usage section for specific commands
# Adapt these to your workflow
Key Responsibilities
- Measure complexity: Calculate cyclomatic complexity, cognitive complexity, and coupling metrics to identify the files that need refactoring most
- Apply pattern-driven refactors: Extract methods, split monoliths, introduce abstractions, remove dead code — each with a defined before/after signature
- Preserve behavior: Run the full test suite before and after every refactoring step to confirm zero behavioral changes
Code Example
"""Minimal refactor agent pattern — analyze and restructure."""
import json, sys
from pathlib import Path
def analyze_complexity(file_path: str) -> dict:
"""Analyze a file for refactoring candidates."""
content = Path(file_path).read_text()
lines = content.split("\n")
functions = []
current_fn = None
fn_lines = 0
branch_count = 0
for i, line in enumerate(lines):
stripped = line.strip()
if stripped.startswith("def ") or stripped.startswith("async def "):
if current_fn:
functions.append({
"name": current_fn, "lines": fn_lines,
"branches": branch_count, "line": i - fn_lines + 1
})
current_fn = stripped.split("(")[0].replace("def ", "").replace("async ", "")
fn_lines = 1
branch_count = 0
elif current_fn:
fn_lines += 1
if any(kw in stripped for kw in ["if ", "elif ", "for ", "while ", "and ", "or "]):
branch_count += 1
if current_fn:
functions.append({
"name": current_fn, "lines": fn_lines,
"branches": branch_count, "line": len(lines) - fn_lines + 1
})
candidates = [f for f in functions if f["branches"] > 10 or f["lines"] > 50]
return {
"file": file_path, "total_lines": len(lines),
"functions": functions,
"candidates": candidates,
"recommendations": [
f"Extract method: {c['name']} ({c['branches']} branches, {c['lines']} lines)"
for c in candidates
]
}
if __name__ == "__main__":
result = analyze_complexity(sys.argv[1])
print(json.dumps(result, indent=2))
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 · 138 lines · 22 tokens per session scan A bbee8736d733
refactor-agent is a skill published in the GitHub repository oyi77/1ai-skills (12 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 1,148 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 skills, from other repositories
create-supervisor
Create, update, list, and safely maintain evidence-bounded graduate-advisor Skills from comments, meeting notes, chat logs, documents, and user corrections. Use when the user asks to create or evolve a supervisor/advisor Skill, distill a mentor's working style, run /create-supervisor, /update-supervisor…
database-migration-helper
Create and manage database migrations safely with rollback support. Use when modifying database schema, adding indexes, or managing database changes.
performance-optimizer
Optimize frontend performance with bundle size reduction, lazy loading, and Core Web Vitals improvements. Use when improving page speed, reducing bundle size, or optimizing Core Web Vitals.
error-handling
Implement Go error handling patterns including error wrapping, sentinel errors, custom error types, and error handling conventions. Use when handling errors, creating error types, or implementing error propagation. Trigger words include "error", "panic", "recover", "error handling", "error wrapping".
inventory-manager
Organizes Ansible inventory files, manages host groups, and configures dynamic inventory. Use when organizing Ansible inventory, managing host groups, or setting up dynamic inventory sources.
terraform-documentation-generator
Generates documentation for Terraform modules using terraform-docs tool to auto-generate README files with input/output tables, usage examples, and requirements. This skill should be used when users need to document Terraform modules, create or update README files, or maintain consistent module documentation.