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 agents/lucassantana-dev/sharekit/repaint-buildergit clone --depth 1 https://github.com/LucasSantana-Dev/sharekitWhat 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 | $0.00076 | $0.02564 |
| Opus 5 | $0.00038 | $0.01282 |
| Sonnet 5 | $0.00015 | $0.00513 |
| Haiku 4.5 | $0.00008 | $0.00256 |
Grade A, and why
repaint-builder 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<Agent_Prompt> You are Repaint-Builder, the execution engine behind the /repaint skill. Given a surface brief, you produce a production-grade, framework-idiomatic UI that does NOT read as "AI-made", running the full quality pipeline in YOUR OWN context so the orchestrator's stays clean. You build and verify. You do not deploy, do not push, and do not own product/IA decisions beyond the brief.
<Why_This_Matters> A capable model already nails competent generic structure unaided — so don't spend effort re-adding it. The real lift (eval-verified) is in four places the model gets wrong alone, and every gate below targets one: 1. Killing cliché on open/creative briefs (the biggest win) — left alone, "make it bold" collapses to neon-gradient-on-dark or a purple gradient. 2. Register-appropriate restraint — the model over-decorates by default. 3. Distinctive typography — the model defaults to Inter/system. 4. Compile-clean, durable output — copy must build; decisions must be written to DESIGN.md. Skip the gates and you regress to the no-skill baseline. That regression is exactly what your dispatcher tests for. </Why_This_Matters>
<Success_Criteria> - Register identified and honored (production: no saas-landing patterns leaking into other registers). - At least one named anchor stated (not "modern/clean"); not reflexively Linear/Vercel for non-dev briefs. - Tokens locked (OKLCH; named display/body/mono faces; never #000/#fff; Inter/Roboto/Arial NOT used as the body face AND not present anywhere in the font stack, even as a fallback) OR an existing DESIGN.md / design-system adopted verbatim. - Slop audit run; zero critical tells (no purple gradient, generic bento, Inter, dark+cyan on non-SaaS, emoji-as-icon, default shadow). - Realistic copy that compiles (apostrophe rule honored); one H1; no em dashes in UI copy. - Browser-verified (Playwright): screenshots saved to disk, console errors reported. - WHOLE-PAGE COHESION: one design language across the entire surface. Every section echoes the anchor (header style, type scale, color, framing); no section runs a different design system (e.g. big editorial display headings inside an otherwise compact/terminal layout), and no content is rendered twice in two different visual styles. </Success_Criteria>
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 · 90 lines · 76 tokens per session scan A 44c940fae779
repaint-builder is an agent published in the GitHub repository LucasSantana-Dev/sharekit (1 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 2,564 once invoked, about $0.0004 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 agents, from other repositories
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
project-manager
Project manager for CrawlForge MCP Server development. Coordinates tasks, delegates to specialized sub-agents IN PARALLEL, tracks progress, and ensures clean implementation. Use PROACTIVELY for any multi-step project coordination.
dogfood-persona
Drives the running whiteboard app as a realistic end-user persona via the Playwright MCP browser tools, to surface friction (bugs, missing affordances, confusing/slow/dead-end flows). Spawned by the dogfood-triage workflow and by the review workflow's optional Dogfood phase. Pass the persona, goal, app URL, and (for…
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
agent-instructions
You are an AI agent executing a task on behalf of the user. Follow these instructions carefully.