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/aldianriski/lean-flow/prototypenpx skills add aldianriski/lean-flow --skill prototypegit clone --depth 1 https://github.com/aldianriski/lean-flowWhat 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 | $0.00085 | $0.00941 |
| Opus 5 | $0.00043 | $0.00470 |
| Sonnet 5 | $0.00017 | $0.00188 |
| Haiku 4.5 | $0.00009 | $0.00094 |
Grade A, and why
prototype 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prototype
A prototype is throwaway code that answers a question. The question decides the shape. It slots
into the design stage — when /orchestrator's Grill can't resolve a design on paper, prototype to
feel the answer, then feed it into the plan.
Pick a branch
Identify the question — from the prompt, the surrounding code, or by asking:
- "Does this logic / state model / API feel right?" → terminal logic prototype. A tiny interactive TUI that drives a state machine by hand through cases that are hard to reason about on paper. Full process →
${CLAUDE_SKILL_DIR}/references/logic.md. - "What should this look like?" → web UI prototype (web projects only). Several radically different UI variations on one route, switchable from a floating bar. Full process →
${CLAUDE_SKILL_DIR}/references/ui.md.
Wrong branch = wasted prototype. If genuinely ambiguous and the user is unreachable, match the surrounding code (backend module → logic; page/component → UI) and state the assumption at the top.
Rules (both branches)
- Throwaway from day one, clearly marked. Locate it next to where it'll be used so context is obvious; name it so a casual reader sees it's a prototype, not production.
- One command to run — via the project's existing task runner. No path to remember.
- No persistence by default — state lives in memory. Persistence is the thing being checked, not depended on. If the question is about the DB, use a scratch store named
PROTOTYPE — wipe me. - Skip the polish — no tests, no error handling beyond runnable, no abstractions, no "what if we need X later". One question.
- Surface the state — after every action (logic) or variant switch (UI), render the full relevant state so the user sees what changed.
- Retire it when done, don't lose it — never leave it rotting on the working branch. Commit the spent prototype to a throwaway branch off main and leave a pointer to that branch beside the captured answer; then delete or absorb it here. The branch costs nothing, keeps the primary source retrievable when the verdict is later questioned, and avoids TD-012's shape — deleting the scaffolding also deleted the fixtures that were guarding something.
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 · 55 lines · 85 tokens per session scan A 87e5c1295280
prototype is a skill published in the GitHub repository aldianriski/lean-flow (4 stars, last pushed 3d ago), licensed MIT. It adds 85 tokens to every session and 941 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 2026-08-31.
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.
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.