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/tsai09495/matt-pocock-engineering/prototypenpx skills add tsai09495/matt-pocock-engineering --skill prototypegit clone --depth 1 https://github.com/tsai09495/matt-pocock-engineeringWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tsai09495/matt-pocock-engineering/prototype)<a href="https://agentmods.dev/skills/tsai09495/matt-pocock-engineering/prototype"><img src="https://agentmods.dev/badge/skills/tsai09495/matt-pocock-engineering/prototype.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00040 | $0.00694 |
| Opus 5 | $0.00020 | $0.00347 |
| Sonnet 5 | $0.00008 | $0.00139 |
| Haiku 4.5 | $0.00004 | $0.00069 |
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 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 — 31 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.
Pick an artifact
Identify which question is being answered — from the user's prompt, the surrounding code, or by asking if the user is around:
- "Does this logic / state model feel right?" → LOGIC.md. Build one self-contained HTML file that exposes the state, free-play controls, and guided walkthroughs for difficult cases.
- "What should this look like?" → UI.md. Generate several radically different UI variations on a single route, switchable via a URL search param and a floating bottom bar.
The two branches produce very different artifacts — getting this wrong wastes the whole prototype. If the question is genuinely ambiguous and the user isn't reachable, default to whichever branch better matches the surrounding code (a backend module → logic; a page or component → UI) and state the assumption at the top of the prototype.
Rules that apply to both
- Throwaway from day one, and clearly marked as such. Before creating files, state the intended prototype location and what question it answers; ask if the location is ambiguous. A standalone logic artifact normally belongs in the OS temp directory. Use a clearly named repository scratch location only when it must reuse project code or runtime conventions. For throwaway UI routes, obey the existing routing convention. Never create a branch or worktree automatically.
- One obvious way to run. A logic prototype opens directly by double-clicking its HTML file. A project-hosted prototype uses one existing task-runner command or one shareable route. Do not add a package manager, server, or build step solely for the prototype.
- No persistence by default. State lives in memory. Persistence is the thing the prototype is checking, not something it should depend on. If the question explicitly involves a database, hit a scratch DB or a local file with a clear "PROTOTYPE — wipe me" name.
- Skip the polish. No tests, no error handling beyond what makes the prototype runnable, no abstractions. The point is to learn something fast and then delete it.
- Surface the state. After every action (logic) or on every variant switch (UI), print or render the full relevant state so the user can see what changed.
- Choose the outcome when done. Present four choices: delete the prototype, retain it temporarily with its throwaway status clear, absorb the validated decision into production work, or preserve it as explicitly approved durable evidence. Ask before deleting files, creating a branch/worktree, writing durable notes, creating an ADR/issue/commit, or modifying production code unless the current request explicitly authorizes that exact outcome.
What ships with it
3 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.
- 3d ago First seen · 31 lines · 40 tokens per session scan A eaa15fde3252
prototype is a skill published in the GitHub repository tsai09495/matt-pocock-engineering (2 stars, last pushed 9d ago), licensed MIT. It adds 40 tokens to every session and 694 once invoked, about $0.0002 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
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
code-comment-generator
Generates meaningful comments and documentation for code to improve maintenance and readability. Use when adding documentation to Python or Java code, including function/method docstrings, class documentation, inline explanations for complex logic, and code annotations (TODO, FIXME). Analyzes existing comment style in…