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.
git clone --depth 1 https://github.com/wei6bin/skillsWrote 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/agents/wei6bin/skills/impl-frontend)<a href="https://agentmods.dev/agents/wei6bin/skills/impl-frontend"><img src="https://agentmods.dev/badge/agents/wei6bin/skills/impl-frontend/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/agents/wei6bin/skills/impl-frontend"><img src="https://agentmods.dev/badge/agents/wei6bin/skills/impl-frontend.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 | $0.00075 | $0.01401 |
| Opus 5.5 | $0.00030 | $0.00560 |
| Sonnet 5.5 | $0.00015 | $0.00280 |
| Haiku 4.5 | $0.00007 | $0.00140 |
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 10d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Impl Frontend
You implement the frontend half of one vertical slice by TDD, one user-visible AC behaviour at a time. Four scopes:
"SLICE-NN frontend half"- build against a typed mock of the card's frozenContract:, concurrently with the backend half. Do not read or wait for the backend and do not integrate; leave the mock in place when you report."SLICE-NN frontend half - kind: sweep"- a mechanical rewrite with no new behaviour: no mock, no contract; the card'sFiles:set and inline verification are the spec (thesweep-implementerskill)."whole-story integration"- every slice has shipped; swap every slice's mock for the real backends in one pass and reconcile drift (thefrontend-implementerskill's "Integration pass"). This is the one scope that ranges across all slices."project scaffold - frontend - skill: {scaffold skill} - root: {dir}"- fromproject-scaffolder, on a repo with no frontend yet: no plan folder and no slice card, just a worktree path and a skeleton contract. Bootstrap the app with the named skill against MSW handlers for the contract, concurrently with the backend half, and stop when its checklist is green.
NO-TOUCH
docs/project_context/**(owned bycontext-updater; pass observations up)- Files in other slices' change-site maps
- Backend files (controllers, services, DTOs, migrations) - flag a needed BE change, never patch it
- Auth/interceptor/route-guard configuration unless your slice's change-site map
lists those lines, or the scope is
project scaffold, where they are the deliverable - Under
project scaffold: anything outside the root the scope names (the backend half is writing its own root in the same worktree)
If a change is needed outside scope, stop and report it under "Flagged".
Before implementing
- Invoke
reuse-ladder. If the slice stands up or repairs the styling standard itself (tokens, Biome enforcement, Tailwind wiring, retiring a legacy CSS vocabulary), also invokefrontend-styling-standard; that work is the slice's own deliverable. House coding conventions are not yours to apply:impl-simplifyconforms the whole-story diff toreact-best-practicesafter every slice ships. Spend this context on the ACs. - Read your slice's card in
04-task-plan.md. Feature tier: also its reference patterns and change sites in03-implementation-plan.md(targets, not an order).kind: sweep, or a refactor-tier story (the folder has only00-overview.mdand04-task-plan.md): the card'sFiles:set and inline verification steps are the whole spec; do not go looking for the other documents. - Read the relevant
docs/project_context/files and follow the project's own conventions where they exist. - In a JS/TS monorepo where the app imports a shared local package, build
workspace deps first (e.g.
pnpm -r build) and again after adding an export to a shared package. The app typechecks against compiled output, which is why the post-edit hook labels the resultingCannot find module/no exported membererrors non-blocking. Rebuild; never edit source to chase them. - Invoke
frontend-implementer, which drives the TDD loop and commits per behaviour, orsweep-implementerinstead when the scope sayskind: sweep.
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.
- 10d ago Changed · +14 lines · +12 tokens per session 1833d2337ff9
- 17d ago Changed · +49 lines · -55 tokens per session 91334d2f2c47
- 1mo ago 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 11d ago), licensed MIT. It adds 75 tokens to every session and 1,401 once invoked, about $0.0003 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 2026-08-31.
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.
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.
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.