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 GongShichen/LuminaCode --skill frontend-implementation-plangit clone --depth 1 https://github.com/GongShichen/LuminaCodeWrote 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/gongshichen/luminacode/frontend-implementation-plan)<a href="https://agentmods.dev/skills/gongshichen/luminacode/frontend-implementation-plan"><img src="https://agentmods.dev/badge/skills/gongshichen/luminacode/frontend-implementation-plan/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gongshichen/luminacode/frontend-implementation-plan"><img src="https://agentmods.dev/badge/skills/gongshichen/luminacode/frontend-implementation-plan.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00021 | $0.00672 |
| Opus 5.5 | $0.00008 | $0.00269 |
| Sonnet 5.5 | $0.00004 | $0.00134 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
Frontend Implementation Plan 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 2mo 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
Write the plan as <project_root>/FRONTEND_PLAN.md.
Size guidance:
- Small CLI/TUI/single-screen work: 60-140 lines.
- Medium feature: 120-220 lines.
- Large app or multi-platform work: expand only where the design/contract requires it.
- Keep the plan actionable: files, state, command/view structure, contract consumption, and tests. Do not restate the whole PRD or UX document.
Inputs:
PRD.mdUX_DESIGN.mdINTERFACE_CONTRACT.mdor an A2A contract draft that must be persisted.- Existing frontend code/conventions, if any.
Required sections:
-
Surface and stack
- Web/mobile/desktop/CLI/TUI/docs/plugin surface.
- Existing conventions, files, framework, or no-framework choice.
- Accessibility and platform constraints.
-
User flows and states
- Happy path.
- Loading, empty, validation error, server/network error, success, disabled/submitting state.
- Focus, keyboard, and screen-reader behavior when relevant.
-
Structure
- Pages/routes/screens/components or command/view layout.
- File structure.
- Ownership of local state and derived display state.
-
Contract consumption
- Exact backend/API/storage/tooling contract consumed.
- Request/response mapping.
- Error mapping.
- For CLI/TUI/local tools with persistence, how subprocesses receive isolated storage during integration tests: environment variable, current working directory convention, config file, fixture path, or command option from the contract.
- Why the implementation is not direct-file, mock-only, or independent.
-
Implementation steps
- Ordered steps that fit frontend ownership.
- What must wait for backend/contract confirmation.
- Integration points to verify with Backend.
- Verification helpers must stay inside expected artifacts. Do not create temporary scripts or extra test files during implementation unless Team Leader included them in expected artifacts.
-
Test and smoke plan
- Unit or simple logic checks.
- Integration smoke against real backend/API.
- Subprocess-based tests must use mechanisms visible to the subprocess. Do not rely on monkeypatching in-process module globals to isolate storage or backend state.
- Do not accept a backend function parameter as subprocess isolation unless the user-facing CLI/API exposes it through the durable contract.
- If
INTERFACE_CONTRACT.mddoes not define a subprocess-visible storage override for a local persistent tool, stop and ask Team Leader/Backend to fix the contract instead of inventing test-only monkeypatches. - Manual UX checks.
- Accessibility checks.
-
Risks and assumptions
- Missing design/contract details.
- Browser/platform compatibility.
- Performance or data-volume concerns.
Do not include backend internals except for the contract you consume. If the contract is not durable, request or create INTERFACE_CONTRACT.md before implementation.
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.
- 2mo ago First seen · 70 lines · 21 tokens per session scan A e244422800b9
Frontend Implementation Plan is a skill published in the GitHub repository GongShichen/LuminaCode (9 stars, last pushed 4d ago), licensed Apache-2.0. It adds 21 tokens to every session and 672 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…