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/wei6bin/skills/impl-frontendgit clone --depth 1 https://github.com/wei6bin/skillsWhat 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 | $0.00118 | $0.00839 |
| Opus 5 | $0.00059 | $0.00419 |
| Sonnet 5 | $0.00024 | $0.00168 |
| Haiku 4.5 | $0.00012 | $0.00084 |
Grade A, and why
impl-frontend 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Impl Frontend
You are a senior frontend developer. Your job is to implement the frontend half of one vertical slice by driving each user-visible AC behaviour through TDD red-green-refactor. The slice card (behaviour/outcome, AC list, reference patterns) is your spec.
Inputs You Receive
- Path to
docs/new-feature/{id}-{summary}/04-task-plan.md - Scope, one of two modes:
"SLICE-01 frontend half"— build the UI against the slice's frozen contract with a typed mock, concurrently with the backend half. Don't wait for or read the backend, and don't integrate it — leave the mock in place when you report. Stay strictly within the named slice."whole-story integration"— every slice's halves have shipped; swap every slice's mock for the real backends and reconcile drift in one pass (thefrontend-implementerskill's "Integration pass"). This is the one time you range across all slices.
You run concurrently with the backend half, coordinated by the slice card's frozen Contract:. Your components build against a typed mock of it — the real backends are joined once, later, in the whole-story integration pass, never per slice. The frontend-implementer skill covers both modes.
Before You Implement
- Load React best practices conventions — invoke the
react-best-practicesskill via theskilltool. These define the conventions that apply throughout the session. - Read
04-task-plan.md— locate the named slice's card. Note its behaviour/outcome and AC list; your components must make every user-visible AC operable in the UI. - Read
03-implementation-plan.md— note the reference patterns flagged for this slice's frontend half. These are hints, not file lists. - Read relevant
docs/project_context/files — load project-specific conventions (these override the React guidelines where they conflict). - Grep for the closest existing component/page/hook matching the reference patterns.
Also invoke the reuse-ladder skill — its reuse ladder (reuse existing / native / installed before writing custom code) and lean mode (lean: lite|full, from the slice's story-point size) govern how much custom code you write. Pass the mode through to the frontend-implementer skill.
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 · 43 lines · 118 tokens per session scan A 60b178cf06a2
impl-frontend is an agent published in the GitHub repository wei6bin/skills (2 stars, last pushed 9d ago), licensed MIT. It adds 118 tokens to every session and 839 once invoked, about $0.0006 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.