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 skills add pax-k/build-right --skill build-right-prototypegit clone --depth 1 https://github.com/pax-k/build-rightWrote 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/pax-k/build-right/build-right-prototype)<a href="https://agentmods.dev/skills/pax-k/build-right/build-right-prototype"><img src="https://agentmods.dev/badge/skills/pax-k/build-right/build-right-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 5.1 | $0.00053 | $0.00766 |
| Opus 5 | $0.00026 | $0.00383 |
| Sonnet 5 | $0.00011 | $0.00153 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
build-right-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 7d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Right Prototype
Use this cross-cutting companion to answer one design question. A prototype is evidence, not product code, customer validation, or permission to implement.
Required Reading
- Read
references/logic.mdfor state, transition, data-shape, or behavioral contract questions. - Read
references/ui.mdfor layout, hierarchy, or interaction questions. - Use
assets/templates/prototype-evidence.mdfor the retained evidence packet. - Read the target repository's instructions, product authority, execution rules, and Git state before creating anything.
Workflow
- State exactly one prototype question and one observable success signal.
- Classify the mode as
logicorui; stop if the question mixes unresolved concerns that cannot be observed together. - Inspect repository conventions and
git status --short. Record unrelated work and do not touch it. - Create the prototype in a disposable temporary directory or detached temporary worktree. Never edit the main worktree by default. If neither safe isolation option is possible, stop and ask.
- Make the prototype runnable with one documented Bun-native command such as
bun run prototypeorbun index.ts. - Run syntax, type, or build smoke verification appropriate to the prototype, plus the smallest assertion that proves the question's success signal.
- Observe the result. Separate what was demonstrated from what remains assumed.
- Write
docs/evidence/prototypes/<slug>.mdin the target repository using the evidence template. This retained packet is the only default main worktree edit. - Route any production implementation through
$build-right-feature-planning. Never copy, move, or promote prototype code directly into production.
Safety Contract
- Use fake, local, or read-only data. Never call a production mutation path.
- Do not use live credentials unless the user explicitly authorizes a bounded, non-mutating proof and repository policy allows it.
- Do not automatically commit, push, merge, publish, deploy, clean up, delete, or promote.
- Do not automatically abort or resolve an existing Git operation.
- Leave disposal or cleanup as an explicit user choice and report the temporary path or worktree.
- Label the finding
prototype-evidencewhen observed andprototype-assumptionwhen it remains inferred.
What ships with it
4 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.
- 7d ago First seen · 80 lines · 53 tokens per session scan A 75e2d0449d6a
build-right-prototype is a skill published in the GitHub repository pax-k/build-right (4 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 766 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.