Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/TrentM6/baseline-corenpx agentmods add skills/trentm6/baseline-core/prototypingWrote 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/trentm6/baseline-core/prototyping)<a href="https://agentmods.dev/skills/trentm6/baseline-core/prototyping"><img src="https://agentmods.dev/badge/skills/trentm6/baseline-core/prototyping/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/trentm6/baseline-core/prototyping"><img src="https://agentmods.dev/badge/skills/trentm6/baseline-core/prototyping.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00036 | $0.02514 |
| Opus 5.5 | $0.00014 | $0.01006 |
| Sonnet 5.5 | $0.00007 | $0.00503 |
| Haiku 4.5 | $0.00004 | $0.00251 |
Grade A, and why
prototyping 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 yesterday.
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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prototyping
Prototyping is about making ideas tangible fast. Not pixel-perfect production code — working demonstrations that let stakeholders experience a concept, test feasibility, and make decisions. The goal is learning and alignment, not shipping.
Core Principles
-
Speed over polish. A prototype that exists today beats a perfect one next month. Get something in front of people fast.
-
Fake what you can, build what you must. Hard-code data, mock integrations, skip edge cases. Only build what's needed to answer the question you're testing.
-
Match fidelity to purpose. A stakeholder demo needs different fidelity than a technical feasibility test. Know what you're proving and build to that level.
-
Throwaway mindset. Prototypes are disposable. Don't get attached. If you're worried about "wasting" the code, you're building too much.
-
One question per prototype. "Does this interaction feel right?" is a prototype. "Is the whole product viable?" is not. Scope ruthlessly.
-
Show, don't describe. A 30-second demo beats a 30-minute explanation. Build the thing, show the thing.
-
Context matters. A prototype shown on a phone feels different than one on a projector. Test in the environment where decisions will be made.
Industry Principles
-
Fidelity spectrum awareness. Paper → Wireframe → Clickable → Coded → Production. Know where you are and why.
-
Technical feasibility is a valid goal. Sometimes the prototype answers "can we build this?" not "should we build this?" Both are valuable.
-
Prototype the risky parts. Focus on what's uncertain or contentious. Don't prototype things everyone already understands.
-
Interactivity reveals truths. Static mockups hide interaction problems. If the value is in the interaction, it must be interactive.
-
Know when to stop. A prototype has served its purpose when you can make a decision. More polish doesn't help.
Workflow
Follow the Workflow Orchestration Pattern for the universal workflow approach. Below are the prototyping-specific details for each step.
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.
- yesterday First seen · 294 lines · 36 tokens per session scan A 3155e267171a
prototyping is a skill published in the GitHub repository TrentM6/baseline-core (23 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 2,514 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-17.
prototyping compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| prototypingTrentM6/baseline-core | Skill | 23 | 2d ago | MIT | A | 36 | Claude Code, Codex |
| webgl-holographic-foilnexu-io/open-design | Skill | 108k | today | Apache-2.0 | A | 41 | Claude Code, Codex |
| html-ppt-hermes-cyber-terminalnexu-io/open-design | Skill | 108k | today | Apache-2.0 | A | 53 | Claude Code, Codex |
| html-ppt-taste-brutalistnexu-io/open-design | Skill | 108k | today | Apache-2.0 | A | 78 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | yesterday | MIT | A | 52 | Codex |
| glance-canonical-layoutsandroid/skills | Skill | 11k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| accessibilitymicrosoft/hve-core | Skill | 1.6k | today | MIT | A | 47 | Claude Code |