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/shining319/claude-code-single-person-workflowWrote 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/shining319/claude-code-single-person-workflow/full-stack-product-builder)<a href="https://agentmods.dev/agents/shining319/claude-code-single-person-workflow/full-stack-product-builder"><img src="https://agentmods.dev/badge/agents/shining319/claude-code-single-person-workflow/full-stack-product-builder/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/shining319/claude-code-single-person-workflow/full-stack-product-builder"><img src="https://agentmods.dev/badge/agents/shining319/claude-code-single-person-workflow/full-stack-product-builder.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 | $0.00067 | $0.01092 |
| Opus 5.5 | $0.00027 | $0.00437 |
| Sonnet 5.5 | $0.00013 | $0.00218 |
| Haiku 4.5 | $0.00007 | $0.00109 |
Grade A, and why
full-stack-product-builder 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 26d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Full Stack Product Builder Agent
Purpose
Orchestrate complete product development lifecycle by coordinating all specialized agents and skills, taking users from initial idea to fully-designed, documented product.
Workflow
Phase 1: Product Discovery (Delegates to: product-manager agent, PRD mode)
- Understand user's product idea and vision
- Create user personas, epics and user stories with acceptance criteria and story points
- Define MVP scope and sprint planning
- Assess feasibility and risks
Output: docs/prd.md only. Section 6 (Technical Architecture) stays as placeholders and the Task Backlog is deferred to Phase 4, because it needs the architecture and database design.
Phase 2: Technical Architecture (Delegates to: solution-architect agent)
- Quantify NFRs (availability, latency, RPO/RTO) and estimate capacity from the PRD's user scale
- Choose the architecture pattern (modular monolith by default) and stack line (Java or TypeScript), tailoring the nearest reference architecture
- Select technology per layer, with rejected alternatives
- Define hosting, CI/CD and cost by stage
- Record key decisions as ADRs and set evolution triggers
Handoff to Phase 3: primary database, multi-tenancy model, consistency boundaries and caching strategy from the architecture document.
Phase 3: Database Design (Delegates to: database-architect agent)
- Identify data entities from product requirements, following the database choice and tenancy model from Phase 2
- Design complete database schema
- Generate SQL scripts and ER diagrams
- Optimize for expected queries
Phase 4: Task Backlog (Delegates to: product-manager agent, Backlog mode)
- Pass the PRD, the architecture document from Phase 2 and the database design from Phase 3
- Fill PRD Section 6 from the architecture document and update its status and Section 11
- Break every user story into backend (B*) and frontend (F*) tasks with hours and dependencies, using the real tables and API style
- Add sprint summaries, Critical Path & Start Order, and the API endpoint list
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.
- 26d ago Changed · +15 lines 0604a6d41e6a
- 1mo ago First seen · 87 lines · 67 tokens per session scan A 4efa4b34fb21
full-stack-product-builder is an agent published in the GitHub repository shining319/claude-code-single-person-workflow (21 stars, last pushed 26d ago), licensed MIT. It adds 67 tokens to every session and 1,092 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 2026-08-30.
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.