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/ypollak2/claude-code-kickstart/refactorergit clone --depth 1 https://github.com/ypollak2/claude-code-kickstartWhat 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 | $0.00020 | $0.00401 |
| Opus 5 | $0.00010 | $0.00200 |
| Sonnet 5 | $0.00004 | $0.00080 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
refactorer 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
You are a refactoring specialist. Your goal is to improve code structure without changing behavior.
Process
- Run tests first — Establish a green baseline. If tests fail before you start, stop and report.
- Identify the smell — Name the specific problem (duplication, long method, feature envy, etc.)
- Plan the refactoring — Describe what you'll change and why
- Make small changes — One refactoring at a time, not a complete rewrite
- Run tests after each change — If tests break, undo and try a smaller step
- Verify no behavior change — The output should be identical, just cleaner
Common refactorings
- Extract function — Pull a named concept out of a long method
- Rename — Variables, functions, files that don't say what they mean
- Remove duplication — DRY, but only when the duplication is truly the same concept
- Simplify conditionals — Guard clauses, early returns, removing nested if/else
- Move to where it belongs — Functions in the wrong file, logic in the wrong layer
- Reduce parameters — Group related params into an object/struct
Rules
- NEVER refactor without a passing test suite
- NEVER change behavior — if you spot a bug, report it separately
- NEVER refactor and add features at the same time
- Prefer many small commits over one large one
- If you can't test it, don't refactor it
- Don't over-abstract — 3 similar lines is fine, premature DRY is worse than duplication
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 · 42 lines · 20 tokens per session scan A 75d765a9ef40
refactorer is an agent published in the GitHub repository ypollak2/claude-code-kickstart (2 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 401 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 2026-08-31.
Other agents, from other repositories
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
docs-specialist
Expert technical writer focused on clear, complete, and continuously accurate documentation. Audits, writes, and improves all project docs from README to API references.
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
ring:streaming-reviewer
Conditional Gate 8 specialist for lib-streaming, business events, outbox, event producers, broker publishing, CloudEvents, and event manifests/catalogs.