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 skills/ao92265/claude-code-playbook/refactornpx skills add ao92265/claude-code-playbook --skill refactorgit clone --depth 1 https://github.com/ao92265/claude-code-playbookWrote 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/ao92265/claude-code-playbook/refactor)<a href="https://agentmods.dev/skills/ao92265/claude-code-playbook/refactor"><img src="https://agentmods.dev/badge/skills/ao92265/claude-code-playbook/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 | $0.00094 | $0.00620 |
| Opus 5 | $0.00047 | $0.00310 |
| Sonnet 5 | $0.00019 | $0.00124 |
| Haiku 4.5 | $0.00009 | $0.00062 |
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 4d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Focused Refactor
Improve code structure without changing behavior. Zero behavior change is non-negotiable.
Steps
-
Establish green baseline:
- Run the full test suite and confirm all tests pass
- Run the type checker (
tsc --noEmit,go vet,cargo check,mypy) - If tests don't exist for the code being refactored, stop and suggest using
/test-first - Record the test results as the baseline
-
Identify the refactoring:
- Clarify what the user wants to improve (or suggest based on code smells)
- Common refactorings: rename, extract function/method, inline, simplify conditionals, remove duplication, split file, consolidate imports
- Scope the change — one refactoring at a time
-
Apply the refactoring:
- Make the minimum changes necessary
- Update all references (imports, call sites, type definitions)
- Preserve all public API contracts
- Don't change test assertions — tests are the behavior contract
-
Verify behavior is preserved:
- Run the full test suite again
- Run the type checker again
- Compare results to baseline — must be identical pass/fail
-
If tests fail — revert immediately:
git checkout -- .to discard changes- Analyze why the refactoring broke tests
- Try a different, safer approach
- Never fix tests to accommodate refactoring — that means behavior changed
-
Final checks:
- Run linter to confirm no new warnings
- Show the diff summary to the user
- Confirm the refactoring achieved the intended improvement
Important
- Zero behavior change is the rule. If any test fails after refactoring, revert. No exceptions.
- Don't combine refactoring with feature work. Refactor in one commit, features in another.
- Tests are the contract. If you need to change tests, you're not refactoring — you're changing behavior.
- One refactoring per pass. Don't rename AND extract AND simplify in one go.
- If no tests exist, stop. Refactoring without tests is guessing. Write tests first.
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.
- 4d ago First seen · 65 lines · 94 tokens per session scan A 48356bd7e954
refactor is a skill published in the GitHub repository ao92265/claude-code-playbook (10 stars, last pushed 17d ago), licensed MIT. It adds 94 tokens to every session and 620 once invoked, about $0.0005 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…