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 keeponfirst/keeponfirst-agentic-workflow-starter --skill keeponfirst-agentic-workflowgit clone --depth 1 https://github.com/keeponfirst/keeponfirst-agentic-workflow-starterWrote 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/keeponfirst/keeponfirst-agentic-workflow-starter/keeponfirst-agentic-workflow)<a href="https://agentmods.dev/skills/keeponfirst/keeponfirst-agentic-workflow-starter/keeponfirst-agentic-workflow"><img src="https://agentmods.dev/badge/skills/keeponfirst/keeponfirst-agentic-workflow-starter/keeponfirst-agentic-workflow/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/keeponfirst/keeponfirst-agentic-workflow-starter/keeponfirst-agentic-workflow"><img src="https://agentmods.dev/badge/skills/keeponfirst/keeponfirst-agentic-workflow-starter/keeponfirst-agentic-workflow.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 | $0.00088 | $0.01842 |
| Opus 5.5 | $0.00035 | $0.00737 |
| Sonnet 5.5 | $0.00018 | $0.00368 |
| Haiku 4.5 | $0.00009 | $0.00184 |
Grade A, and why
keeponfirst-agentic-workflow 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 1mo 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Workflow Skill (v2.4)
An 8-phase development workflow that coordinates multiple AI agents to deliver high-quality features, with enhanced UI quality controls and updated toolchain integration.
Pipeline
INSIGHTS(0) → PLAN(1) → WIREFRAME GATE(1.5) → ASSETS(2) → DESIGN(2.5) → CODE(3) → REVIEW(4) → RELEASE(5)
- UI Tasks: Full pipeline required
- Logic-only Tasks: Skip phases 0, 1.5, 2.5 (note in PLAN)
Agent Roles
| Agent | Role | Tool |
|---|---|---|
| Antigravity | Orchestrator - plans, reviews, releases | This AI |
| Nano Banana | Asset Generator - creates images | MCP / Prompt Files |
| Stitch | UI Designer - generates screens (Vibe Design / Infinite Canvas) | MCP / Web |
| Jules | Cloud Coder - implements in background (parallel supported) | CLI |
Phase 0: INSIGHTS
Output: research/<feature>.md
Skip for logic-only tasks (note in PLAN).
Required content:
- User pain points (Jobs-to-be-done)
- Similar patterns (3-5 examples)
- Anti-patterns to avoid
- Visual direction candidates (A/B/C)
- Recommendation
Human Gate: Problem definition ✓, Visual direction (A/B/C) ✓
Phase 1: PLAN
Output: plans/<feature>.md
Required content:
- Scope (In/Out)
- Technical Design
- Task breakdown
- Acceptance Criteria
- Decision Snapshot
Human Gate: Scope ✓, Data Model ✓, Risk ✓, Enter Wireframe? ✓
Phase 1.5: WIREFRAME GATE
Output: wireframes/<feature>_A.md, wireframes/<feature>_B.md, wireframes/<feature>_decision.md
Skip for logic-only tasks.
Compare structure before style. Each version must include:
- Screen structure & info hierarchy
- Primary flow (shortest path)
- Tap map (thumb-zone analysis)
Human Gate: Select A/B/Redo ✓, Critical interactions ✓
Phase 2: ASSETS
Output: assets/generated/<feature>/
Option A: Generate Prompt Files (Default)
Create .prompt.md files in nanobanana/queue/ for manual or browser-automated execution:
---
output_path: assets/generated/<feature>/hero.png
aspect_ratio: 16:9
---
# Hero Image
Create a modern illustration showing...
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 225 lines · 88 tokens per session scan A b82f5d93a786
keeponfirst-agentic-workflow is a skill published in the GitHub repository keeponfirst/keeponfirst-agentic-workflow-starter (21 stars, last pushed 3mo ago), licensed MIT. It adds 88 tokens to every session and 1,842 once invoked, about $0.0004 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…