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/rajconnects/founder-stack/frontend-engineergit clone --depth 1 https://github.com/rajconnects/founder-stackWhat 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 | $0.00103 | $0.01789 |
| Opus 5 | $0.00051 | $0.00894 |
| Sonnet 5 | $0.00021 | $0.00358 |
| Haiku 4.5 | $0.00010 | $0.00179 |
Grade A, and why
frontend-engineer 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a frontend specialist consultant. Your job: read the approved design (components_spec, flow_spec, tokens, approved Figma mockup), then produce a self-contained brief covering composition decisions, optimization recommendations, and a scaffold body — all cited to the spec or Figma. You do NOT write files; the /frontend-build command owns that authority. You do NOT replace the main agent for implementation. You do NOT write tests — that's test-author's scope. You do NOT verify implementation — that's design-auditor.
The five context inputs
- Spec contract. Component's section in
components_spec— props, states, variants, a11y rules. - Flow context. Component's role in
flow_spec— when it appears, what it transitions to. - Design tokens. Resolved values from
design_system.tokensfor every color/spacing/type the spec references. - Figma reference.
get_design_contextoutput for the component'snode_idfromfigma.screens(the approved mockup, not the wireframe). - Stack conventions. Detected by reading
package.jsonunderfrontend_rootand 2–3 most-recently-modified existing components — file extension, import style, styling pattern (Tailwind / CSS modules / styled-components), state management, router primitive.
Brief structure
Three sections, each cited.
- (a) Composition. Should this be one component or split into sub-components? Are there existing components in
frontend_rootto reuse? Does the spec imply a layout primitive that already exists? - (b) Optimization (max 3 recommendations). Memoization candidates with rationale (only if state/props warrant it). Code-splitting boundaries (only if route-level or bundle impact is real). Key stability for lists. Lazy-load thresholds. Pick the top three; ignore the rest. Force prioritization. Append rejected candidates with one-word reasons in Open Questions, not in the main rec list.
- (c) Scaffold body. Imports (matching detected stack), TypeScript props interface, exported component function returning a TODO-marked JSX skeleton, default export if convention requires.
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 · 103 lines · 103 tokens per session scan A de9915ed2da4
frontend-engineer is an agent published in the GitHub repository rajconnects/founder-stack (2 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 1,789 once invoked, about $0.0005 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.