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/yoursshlabs/yourssh/yourssh-refactor-sweepnpx skills add YoursshLabs/yourssh --skill yourssh-refactor-sweepgit clone --depth 1 https://github.com/YoursshLabs/yoursshWhat 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 | $0.00071 | $0.00800 |
| Opus 5 | $0.00036 | $0.00400 |
| Sonnet 5 | $0.00014 | $0.00160 |
| Haiku 4.5 | $0.00007 | $0.00080 |
Grade A, and why
yourssh-refactor-sweep 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.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YourSSH Refactor Sweep
Review the Flutter codebase for optimization opportunities and apply the safe, behavior-preserving ones. Optimize for high-confidence wins; defer risky changes for explicit sign-off.
When to use
- User asks to "review và refactor", "tối ưu", "clean up", "find dead code" over an area or the whole project.
- After a feature lands and the code needs a tidy pass.
Do not use when: the user wants a single targeted bug fix (use superpowers:systematic-debugging) or a behavioral change/new feature (use superpowers:brainstorming).
Four categories to scan
- Performance — excess
notifyListeners(), work inbuild()/getters called per frame, repeated I/O, O(n) lookups that should be aMap/Set, redundant parsing. - Duplication — repeated logic → shared helper/extension/top-level function.
- Readability — long functions, deep nesting, huge
build()→ split into methods or extracted widgets. - Dead code — unused private methods/fields/imports, unreachable branches.
Workflow
-
Scope first. If the request is broad, use
AskUserQuestionto pin down: which categories, and which area (app/lib/services,app/lib/providers, wholeapp/lib, orpackages/). Don't sweep blind — it burns tokens. -
Map size.
find app/lib -name '*.dart' | xargs wc -l | sort -rn | head -40to find the heavy files. -
Fan out (parallel). Dispatch
Exploresubagents — one per area (services / providers / widgets) — to return concrete findings:file:line+ category + one-line problem + suggested fix. Tell them: high-confidence only, no style nitpicks, prioritize by impact. -
Filter to safe wins. Apply ONLY behavior-preserving changes. Verify each finding by reading the actual code before editing (agents over-report). Good defaults:
- Merge identical methods; extract repeated predicates/loops into a helper.
- Guard
notifyListeners()with an equality check (if (_x == v) return;). - Replace long
switch/.any()per-frame scans withMap/Setlookups. - Extract a large
ListView.builderrow into aStatelessWidget(better element reuse); split a >150-linebuild()into private_buildXmethods or sub-widgets. - Pull repeated
InputDecoration/styling into a helper.
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 · 51 lines · 71 tokens per session scan A fc6ba164d5fc
yourssh-refactor-sweep is a skill published in the GitHub repository YoursshLabs/yourssh (40 stars, last pushed 9d ago), licensed MIT. It adds 71 tokens to every session and 800 once invoked, about $0.0004 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…