prototype

A throwaway prototyping workflow for answering one design question through a small terminal program or several switchable user-interface versions.

In plain words
What is it for?
Use it to explore backend behavior with a small interactive terminal app or compare three to five UI layouts on one page.
Why use it?
It lets you test logic, state, API shape, or page layout before committing to production code. The prototype is documented for later use and is meant to be deleted or incorporated afterward.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/yugasun/aiops/prototype
Any agent
npx skills add yugasun/aiops --skill prototype
Clone the repo
git clone --depth 1 https://github.com/yugasun/aiops

Made for: Claude Code, Codex.

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 374 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00023 $0.00374
Opus 5 $0.00012 $0.00187
Sonnet 5 $0.00005 $0.00075
Haiku 4.5 $0.00002 $0.00037

Measured 2d ago against content hash cea4ce273e52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

skills/prototype/SKILL.md · 37 lines

What it actually says

Prototype

Throwaway code that answers one question. Capture the answer in NOTES.md (required before PRD or /aiops-implement absorption).

Pick a branch

  • Logic / state / API shape → tiny interactive terminal app. Pure logic module + thin TUI shell. One command to run. In-memory state unless persistence is the question.
  • Look and layout → 3–5 structurally different UI variants on one route, switchable via ?variant= and a floating bottom bar. Prefer embedding in an existing page over a new route.

If ambiguous: match surrounding code (backend → logic; page → UI) and state the assumption.

Rules (both branches)

  1. Name and locate so it's obviously throwaway, near the code it informs.
  2. One command to run (pnpm, python, etc.).
  3. No tests, minimal error handling, no abstractions beyond the question.
  4. Surface full state after each action or variant switch.
  5. Delete or absorb when done — don't leave rot.

Logic branch

  • State the question in one paragraph before coding.
  • Isolate logic in a portable pure module (reducer, state machine, or pure functions). TUI is throwaway.
  • TUI: clear screen each tick, show state + keyboard shortcuts, loop until quit.

UI branch

  • Variants must differ in layout/hierarchy, not just color.
  • Switcher: bottom bar, URL param, arrow keys (skip when input focused), hidden in production.
  • Winner gets folded into real code; losers and switcher deleted.
Changes

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.

  1. 2d ago First seen · 37 lines · 23 tokens per session scan A cea4ce273e52

Subscribe to this mod's changes

prototype is a skill published in the GitHub repository yugasun/aiops (4 stars, last pushed 13d ago), licensed Apache-2.0. It adds 23 tokens to every session and 374 once invoked, about $0.0001 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.