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/panda850819/verbs/prototypenpx skills add panda850819/verbs --skill prototypegit clone --depth 1 https://github.com/panda850819/verbsWhat 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 | $0.00064 | $0.00740 |
| Opus 5 | $0.00032 | $0.00370 |
| Sonnet 5 | $0.00013 | $0.00148 |
| Haiku 4.5 | $0.00006 | $0.00074 |
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 — 74 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; the verdict outlives the code.
Pick the branch
Identify the question from the prompt and the surrounding code. If genuinely ambiguous, ask when the user is present; otherwise match the surrounding code (backend module → logic; page or component → UI) and state the assumption at the top of the prototype. Getting the branch wrong wastes the whole prototype.
- "Does this logic / state model feel right?" → LOGIC.md: a tiny interactive terminal app that pushes the state model through cases that are hard to reason about on paper.
- "What should this look like?" → UI.md: several structurally
different variants on one route, switchable via
?variant=and a floating bottom bar. Single round by default; UI.md's converge mode runs repeated rounds down the visual design tree when the user (or a Decision Map entry) asks for it. Converge still only chooses a direction, at finer grain — it never becomes the production build.
Rules (both branches)
- Throwaway from day one, clearly marked. Locate it next to the module or page it prototypes so context is obvious; name it so a casual reader sees prototype, not production. Obey the project's existing routing and task conventions — invent no new top-level structure.
- One command to run, via the project's existing task runner. The user starts it without thinking.
- No persistence by default. State lives in memory. If the question is explicitly about persistence, hit a scratch store named "PROTOTYPE — wipe me".
- Skip the polish. No tests, no error handling beyond what makes it runnable, no abstractions. The point is to learn fast.
- Surface the state. After every action (logic) or variant switch (UI), show the full relevant state so the user sees what changed.
Capture when done
Done means the question is answered AND captured:
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 · 74 lines · 64 tokens per session scan A 739d46fa80c4
prototype is a skill published in the GitHub repository panda850819/verbs (5 stars, last pushed 9d ago), licensed MIT. It adds 64 tokens to every session and 740 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 2026-08-31.
Other skills, from other repositories
processing-markdown
Processes Markdown files using mq, a jq-like query language for Markdown. Use when the user mentions Markdown processing, content extraction, document transformation, or mq queries.
markstream-react
Integrate the beta markstream-react package into a React 18+ or Next app. Use when Codex needs to add the React renderer, choose the root, next, or server entrypoint, import CSS correctly, choose between content and nodes, keep client boundaries safe, add renderer-local streamingComponents or htmlComponents, use…
web-scraping
Fetches web pages and extracts structured data using mq's toolchain (mq-crawl for fetching/crawling/JS rendering, mq for HTML-to-Markdown selector-based extraction, http() for in-query requests). Use when the user wants to scrape a URL, pull structured data out of a webpage, crawl a site, or turn HTML into…
markstream-vue2-cli
Integrate markstream-vue2 into a Vue 2 Vue CLI or Webpack 4 app. Use when Codex needs Webpack 4-friendly setup, CDN worker fallbacks for Mermaid or KaTeX, dist/index.css imports, Vue 2 composition-api shims, or code block choices limited to stream-diffs or plain .
markstream-svelte
Integrate the beta markstream-svelte package in Svelte 5 or SvelteKit apps. Use when Codex needs Svelte 5 runes, CSS and optional peers, smooth streaming, worker setup, renderer-local or scoped custom components, or SSR-safe boundaries. Svelte 4 is unsupported.
decided-import
Reformat ONE existing document (a decision, requirement, design, roadmap, or prompt) into ONE valid RAC (requirements-as-code) artifact, with a mandatory human-review step before any file is written and decided validate as the deterministic close. Use when a user wants to add or import a single existing decision or…