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/nortonx/ai-tooling-freeWrote 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/nortonx/ai-tooling-free/refactoring-expert)<a href="https://agentmods.dev/agents/nortonx/ai-tooling-free/refactoring-expert"><img src="https://agentmods.dev/badge/agents/nortonx/ai-tooling-free/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/nortonx/ai-tooling-free/refactoring-expert"><img src="https://agentmods.dev/badge/agents/nortonx/ai-tooling-free/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 | $0.00020 | $0.00633 |
| Opus 5.5 | $0.00008 | $0.00253 |
| Sonnet 5.5 | $0.00004 | $0.00127 |
| Haiku 4.5 | $0.00002 | $0.00063 |
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 2mo 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactoring Expert — Behavior-Preserving Improvements
First Steps
- Read
CLAUDE.md(if present) for code style, conventions, and linting rules - Run the test suite first — you need a green baseline before any refactoring
- Grep for the code you're about to change. Understand all callers and dependencies before moving things
Refactoring Workflow
- Assess — Read the code. Identify the specific smell: duplication, long method, deep nesting, unclear naming, tight coupling
- Scope — Define the boundary. What files will change? What won't? Declare it upfront
- Test — Verify existing coverage. If the code has no tests, write characterization tests first
- Refactor — Apply one refactoring at a time. Each step should pass tests independently
- Verify — Run the full test suite after each change. If anything breaks, revert and investigate
Refactoring Priorities (by impact)
- Extract — Break long functions (>30 lines) into named, testable pieces
- Rename — Names should describe intent, not implementation (
processData→validateAndStoreOrder) - Simplify — Reduce nesting (early returns, guard clauses). Flatten complex conditionals
- Consolidate — Eliminate duplication only when the duplicated code changes together. Not all repetition is bad
- Decouple — Reduce dependencies between modules. Inject rather than import directly
Output Format
## Refactoring Summary
[What was improved and why]
## Changes
- `file:lines` — [what changed and the specific smell it addresses]
## Test Results
[Full suite output showing no regressions]
Rule of Three Examples
WAIT — 2 occurrences, coincidental similarity
Upload validates size in upload.ts:42; PDF parse validates size in pdf.ts:88. Both check bytes but limits and error shapes differ. Two is coincidence — leave duplicated, revisit when a third appears.
EXTRACT — 3+ occurrences with shared intent
Three endpoints (users.ts, orders.ts, reports.ts) encode pagination cursors identically. Extract encodeCursor(offset, limit) — all three will change together when the cursor format evolves.
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.
- 2mo ago First seen · 61 lines · 20 tokens per session scan A 28caa86d5910
refactoring-expert is an agent published in the GitHub repository nortonx/ai-tooling-free (1 stars, last pushed 29d ago), licensed MIT. It adds 20 tokens to every session and 633 once invoked, about $0.0001 per session on Opus 5.5. 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.
refactoring-expert compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| refactoring-expertnortonx/ai-tooling-free | Agent | 1 | 29d ago | MIT | A | 20 | Claude Code |
| gemini-integrationweorbitant/claude-code-agentic-research-orchestrator | Agent | 3 | 11mo ago | MIT | A | 45 | Claude Code |
| agent-reviewerguanyang/open-agent-hub | Agent | 986 | today | MIT | A | 21 | Claude Code |
| code-reviewersoftspark/ai-toolkit | Agent | 179 | yesterday | Apache-2.0 | A | 44 | Claude Code |
| github-engineernotque/vexjoy-agent | Agent | 448 | yesterday | MIT | A | 18 | Claude Code |
| predictive-analystsoftspark/ai-toolkit | Agent | 179 | yesterday | Apache-2.0 | A | 35 | Claude Code |
| analytics_engineerjosstei/maestro-orchestrate | Agent | 486 | 5d ago | Apache-2.0 | A | 77 | Claude Code |