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 vfarcic/dot-ai --skill dot-ai-prd-startgit clone --depth 1 https://github.com/vfarcic/dot-aiWrote 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/vfarcic/dot-ai/dot-ai-prd-start)<a href="https://agentmods.dev/skills/vfarcic/dot-ai/dot-ai-prd-start"><img src="https://agentmods.dev/badge/skills/vfarcic/dot-ai/dot-ai-prd-start/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/vfarcic/dot-ai/dot-ai-prd-start"><img src="https://agentmods.dev/badge/skills/vfarcic/dot-ai/dot-ai-prd-start.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00013 | $0.01708 |
| Opus 5 | $0.00006 | $0.00854 |
| Sonnet 5 | $0.00003 | $0.00342 |
| Haiku 4.5 | $0.00001 | $0.00171 |
Grade A, and why
dot-ai-prd-start 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 9d 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Start - Begin Implementation Work
Instructions
You are helping initiate active implementation work on a specific Product Requirements Document (PRD). This command sets up the implementation context (validates readiness, creates branch, prepares environment) then hands off to /prd-next for task identification.
IMPORTANT: Do NOT include time estimates or effort estimates in your responses. Focus on setup and readiness without speculating on duration.
Process Overview
- Select Target PRD - Identify which PRD to implement
- Validate PRD Readiness - Ensure the PRD is ready for implementation
- Set Up Implementation Context - Create branch and prepare environment
- Hand Off to prd-next - Delegate task identification to the appropriate prompt
Step 0: Check for PRD Argument
If prdNumber argument is provided ({{prdNumber}}):
- Skip context check and auto-detection
- Use PRD #{{prdNumber}} directly
- Proceed to Step 2 (PRD Readiness Validation)
If prdNumber argument is NOT provided:
- Continue to context awareness check below
Step 0b: Context Awareness Check
Check if PRD context is already clear from recent conversation:
Skip detection if recent conversation shows:
- Recent PRD work discussed - "We just worked on PRD 29", "Just completed PRD update", etc.
- Specific PRD mentioned - "PRD #X", "MCP Prompts PRD", etc.
- PRD-specific commands used - Recent use of
/prd-update-progress,/prd-startwith specific PRD - Clear work context - Discussion of specific features, tasks, or requirements for a known PRD
If context is clear:
- Skip to Step 2 (PRD Readiness Validation) using the known PRD
If context is unclear:
- Continue to Step 1 (PRD Detection)
Step 1: Smart PRD Detection (Only if Context Unclear)
Auto-detect the target PRD using these context clues (in priority order):
- Git Branch Analysis - Check current branch name for PRD patterns:
feature/prd-12-*→ PRD 12prd-13-*→ PRD 13feature/prd-*→ Extract PRD number
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.
- 9d ago First seen · 202 lines · 13 tokens per session scan A faecad4708a2
dot-ai-prd-start is a skill published in the GitHub repository vfarcic/dot-ai (336 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 1,708 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…