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/okwinds/miscellany/skill-create-flownpx skills add okwinds/miscellany --skill skill-create-flowgit clone --depth 1 https://github.com/okwinds/miscellanyWhat 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 | $0.00063 | $0.01538 |
| Opus 5 | $0.00032 | $0.00769 |
| Sonnet 5 | $0.00013 | $0.00308 |
| Haiku 4.5 | $0.00006 | $0.00154 |
Grade A, and why
skill-create-flow 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.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Create Flow
Build a new skill using a repeatable, high-signal workflow that separates methodology discovery from packaging**—without requiring any other skills to be installed or invoked.
Best for
This workflow excels at creating procedural agent skills where the value comes from following a structured methodology rather than raw knowledge retrieval.
Ideal skill types:
- Methodology-based: Debugging, code reviews, writing specs, systematic problem-solving
- Decision-heavy: Architecture decisions, UX design, business strategy, negotiation
- Multi-step workflows: Defined sequence of operations with clear deliverables
- Quality-focused: Where "excellent vs mediocre" output is distinguishable
Less ideal for:
- Pure reference/lookup skills (use knowledge retrieval instead)
- Simple one-shot commands (use direct tool invocation instead)
- Skills requiring external dependencies (this flow produces standalone skills)
Scope & Outputs
You are producing a new skill folder (with its own SKILL.md and optional bundled resources). This flow helps you:
- Narrow the intent until “excellent vs mediocre” is judgeable.
- Extract expert frameworks (when needed).
- Generate a production-ready, testable skill spec and artifacts.
Target artifacts (recommended)
SKILL.mdexamples/(1 tiny example)tests/(3–5 eval prompts or scenarios)index_entry.json(if you maintain a skill index)CHANGELOG.md(optional but helpful for iteration)
Decision Rules (Pick the Track)
Track A — Non-technical / judgment-heavy (default if unsure)
Examples: writing, sales, hiring, product decisions, strategy, negotiation.
Use the full flow below (steps 1–6).
Track B — Technical / objective correctness dominates
Examples: code generation patterns, CLI automation, infrastructure scripts, data pipelines.
Usually shorten Step 2 (“expert frameworks”) and spend more time on Step 5 (“validation”).
Workflow (Standalone)
What ships with it
2 files 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.
- 2d ago First seen · 187 lines · 63 tokens per session scan A bf554b36044f
skill-create-flow is a skill published in the GitHub repository okwinds/miscellany (50 stars, last pushed 3mo ago), licensed MIT. It adds 63 tokens to every session and 1,538 once invoked, about $0.0003 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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.