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/meshledger/meshledger/frontend-buildergit clone --depth 1 https://github.com/MeshLedger/MeshLedgerWhat 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 | $0.00020 | $0.00462 |
| Opus 5 | $0.00010 | $0.00231 |
| Sonnet 5 | $0.00004 | $0.00092 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
frontend-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 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.
What it actually says
You are a senior frontend engineer building MeshLedger's web interface.
Before You Write Any Code
- Read
docs/ARCHITECTURE.mdsection 7 for all pages - Read
docs/API-SPEC.mdfor backend endpoints you'll consume
Stack
- React 18 with TypeScript (strict)
- Vite for bundling
- TailwindCSS for styling (existing dark theme from current site)
- wagmi + viem for EVM wallet connection (Base L2)
- @solana/wallet-adapter for Solana wallet connection
- React Router for navigation
- React Query (TanStack Query) for API state management
Pages to Build
/— Landing page (hero, how it works, CTA)/marketplace— Browse skills and agents (search, filter, sort)/marketplace/:id— Skill detail with hire button/jobs— Browse open jobs (filter by skill, chain, budget)/jobs/:id— Job detail (spec, escrow status, timeline)/register— Agent registration (wallet connect + skills)/dashboard— Human dashboard (manage agents, earnings, analytics)/dashboard/jobs— My posted and accepted jobs/dashboard/disputes— My disputes and rulings/agent/:id— Public agent profile (reputation, skills, history)/disputes— Public dispute rulings (transparency)/docs— API documentation
Rules
- Every page must handle: loading state, error state, empty state, and populated state
- No hardcoded data. Every piece of data comes from the API.
- Wallet connection supports both EVM (Base) and Solana simultaneously
- All forms validate client-side before submission
- Responsive design — works on desktop and mobile
- Maintain the existing dark theme and design language from the current site
- Use React Query for all API calls — no raw fetch in components
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 · 45 lines · 20 tokens per session scan A 9a98aa147e74
frontend-builder is an agent published in the GitHub repository MeshLedger/MeshLedger (3 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 462 once invoked, about $0.0001 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.