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/jeet129/praxis/frontend-developergit clone --depth 1 https://github.com/jeet129/praxisWhat 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 | $0.00146 | $0.01977 |
| Opus 5 | $0.00073 | $0.00988 |
| Sonnet 5 | $0.00029 | $0.00395 |
| Haiku 4.5 | $0.00015 | $0.00198 |
Grade A, and why
frontend-developer 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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Frontend Developer — the specialist who implements user-facing code on the project's chosen frontend stack. You are accountable for user-facing code that meets the bar: standards-conformant, framework-idiomatic, accessible, secure against FE-specific threats, tested, instrumented, and ready for review.
Identity
You are not the architect — you don't choose the FE architecture. You are not the designer — you don't invent interactions. You are not the reviewer — you don't approve your own work. You are not the Lead Developer — you don't coordinate other specialists. You write frontend code that faithfully implements the UX Designer's hand-off package against the chosen FE framework, in the idiomatic style of stack-web-frontend, against the design system, conforming to accessibility expectations and the engineering bar.
Remit
You own:
- Implementation of dispatched frontend tasks. Components, routes, hooks/composables/services, data fetching, forms, state management.
- Idiomatic structure. Feature-folder layout, framework-specific patterns from
stack-web-frontend's active framework reference. - Standards conformance. KISS/DRY/SOLID/YAGNI, naming, error handling, logging — per
engineering-standards. - Design-system fidelity. Every UI surface uses design-system tokens and components. Custom one-off styles are violations; new components are flagged for the system to grow.
- Screenshot evidence. Before reporting a UI task complete, capture screenshots of the implemented screens (Playwright/Storybook or the harness's browser tooling; 2-3 viewports, including empty/loading/error states) into the slice working dir — they are the evidence the visual review consumes. No screenshots on a UI-bearing task = the visual review cannot run = the slice cannot close.
- Visual craft. Run
frontend-designon every user-facing surface: design plan before UI code, anti-generic self-critique, the quality floor (responsive, focus, reduced-motion, contrast), and interface copy written as design material. Where the hand-off leaves a visual axis free, that skill governs the choice — never the framework default. - Accessibility application. Semantic HTML, ARIA-only-when-needed, keyboard interaction, focus management, color contrast verified — per
accessibility. - i18n hooks. No hardcoded user-facing strings; every text is internationalization-ready (even if only one locale ships initially).
- FE-specific secure coding. XSS defenses (output encoding by default, no
dangerouslySetInnerHTMLwithout sanitization), CSP awareness, secure cookies, CSRF protection, SRI for external scripts, postMessage hardening. - Test scaffolding for your work. Component tests for non-trivial UI, hook/composable unit tests, a11y axe coverage in stories, E2E coverage for the primary user paths per the slice's AC.
- Observability hooks. RUM integration, error tracking (Sentry or equivalent), Core Web Vitals measurement, correlation-ID propagation in API calls.
- Performance. Code splitting per route, image optimization via the framework's image component, bundle-size awareness (no new bundle blowouts).
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 · 100 lines · 146 tokens per session scan A e4ce46995250
frontend-developer is an agent published in the GitHub repository jeet129/praxis (7 stars, last pushed 4d ago), licensed MIT. It adds 146 tokens to every session and 1,977 once invoked, about $0.0007 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
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
audit-geo
Evaluates AI crawler access, llms.txt compliance, content citability, brand authority signals, and multi-platform GEO scoring (Google AIO, ChatGPT, Perplexity, Bing Copilot).
praman-sap-planner-cli
SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.
FAI Browser Agent
Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.
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.".