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/penwyp/claudepreference/refactor-design-reportnpx skills add penwyp/ClaudePreference --skill refactor-design-reportgit clone --depth 1 https://github.com/penwyp/ClaudePreferenceWrote 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/penwyp/claudepreference/refactor-design-report)<a href="https://agentmods.dev/skills/penwyp/claudepreference/refactor-design-report"><img src="https://agentmods.dev/badge/skills/penwyp/claudepreference/refactor-design-report.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 | $0.00092 | $0.01083 |
| Opus 5 | $0.00046 | $0.00541 |
| Sonnet 5 | $0.00018 | $0.00217 |
| Haiku 4.5 | $0.00009 | $0.00108 |
Grade A, and why
refactor-design-report 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactor Design Report
Purpose
Create a durable engineering report that turns concrete problems into an executable design. Ground the report in the current code and contracts first, then describe the target model, backend changes, frontend changes, validation strategy, implementation order, and acceptance criteria.
Workflow
-
Normalize the request.
- Extract the concrete issues, desired behavior, affected user flows, and any stated constraints.
- Separate current defects from desired future capabilities.
- If the user says to persist the result, write a focused design document in the appropriate docs location; otherwise provide the report in the reply.
-
Locate the real implementation.
- Find entry points before designing: API definitions, handlers, service methods, data models, workflow runners, frontend request builders, UI components, tests, and docs.
- Prefer real call paths over keyword-level guesses.
- Identify what is already implemented, what is only documented, and what is missing.
-
Define the target semantics.
- Name the core concepts and states precisely.
- State invariant rules as hard requirements, not suggestions.
- Resolve ambiguous user-facing terms into exact technical meanings.
- Decide which behavior belongs in backend hard validation, frontend guidance, workflow preflight, and tests.
-
Design the backend.
- Cover API/proto/schema changes, storage changes, service validation, workflow/runtime changes, error types, idempotency, locking, and retry behavior.
- Put hard safety rules in backend paths that cannot be bypassed by the UI.
- Include both precheck-time and execution-time validation when state can change between submit and execution.
-
Design the frontend.
- Cover UI state, available actions, disabled states, warnings, confirmations, request shape, response handling, and stale precheck protection.
- Ensure user wording matches the actual backend semantics.
- Prevent users from selecting impossible or unsafe combinations; still rely on backend validation as final authority.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 128 lines · 92 tokens per session scan A fc3b6f7548dc
refactor-design-report is a skill published in the GitHub repository penwyp/ClaudePreference (137 stars, last pushed 3mo ago), licensed MIT. It adds 92 tokens to every session and 1,083 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 2026-08-30.
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…