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 commands/jsk9999/ai-nexus/refactorgit clone --depth 1 https://github.com/JSK9999/ai-nexusWrote 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/commands/jsk9999/ai-nexus/refactor)<a href="https://agentmods.dev/commands/jsk9999/ai-nexus/refactor"><img src="https://agentmods.dev/badge/commands/jsk9999/ai-nexus/refactor.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 | $0.00005 | $0.00224 |
| Opus 5 | $0.00003 | $0.00112 |
| Sonnet 5 | $0.00001 | $0.00045 |
| Haiku 4.5 | $0.00001 | $0.00022 |
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 3d 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
When asked to refactor code:
- Analyze first — Read the entire file before making changes
- Identify issues — List specific problems (duplication, complexity, naming)
- Propose changes — Explain what you'll change and why
- Preserve behavior — Refactoring must not change functionality
- Verify — Run existing tests after refactoring
Refactoring Checklist
- Extract repeated code into functions
- Simplify nested conditionals (guard clauses, early returns)
- Rename unclear variables and functions
- Split large functions (> 50 lines)
- Split large files (> 300 lines)
- Remove dead code
- Replace magic numbers with named constants
Rules
- Make one type of change at a time
- Keep each change small and reviewable
- Don't add features during refactoring
- Don't change formatting during logic refactoring
- If tests don't exist, write them before refactoring
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.
- 3d ago First seen · 31 lines · 5 tokens per session scan A 8da73f759d93
refactor is a command published in the GitHub repository JSK9999/ai-nexus (18 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 5 tokens to every session and 224 once invoked, about $0.0000 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 commands, from other repositories
eval
Evaluate and improve one healthcare agent's system prompt. Run up to 5 iterations of: prepare fixed questions -> answer -> judge -> improve -> re-score -> commit if better.
csm-workledger
Show the surviving work-ledger entries across sessions.
scaffold-frontend-project
Scaffold a new frontend project following the 5-layer Clean Architecture (Domain, Service, Infrastructure, Presentation, Main).
scaffold-python-package
Scaffold a new Python package following PEP 621, PDM, Black/isort/Flake8, type hints, and Loguru logging.
matcha:audit
🍵 Stack health check — find overlaps, waste, and risks before they become problems.
session-info
Copy project path, session title, and session ID to clipboard (no LLM round-trip).