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 thangchung/agent-engineering-experiment --skill prdgit clone --depth 1 https://github.com/thangchung/agent-engineering-experimentWrote 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/thangchung/agent-engineering-experiment/prd)<a href="https://agentmods.dev/skills/thangchung/agent-engineering-experiment/prd"><img src="https://agentmods.dev/badge/skills/thangchung/agent-engineering-experiment/prd/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/thangchung/agent-engineering-experiment/prd"><img src="https://agentmods.dev/badge/skills/thangchung/agent-engineering-experiment/prd.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 | $0.00034 | $0.01007 |
| Opus 5.5 | $0.00014 | $0.00403 |
| Sonnet 5.5 | $0.00007 | $0.00201 |
| Haiku 4.5 | $0.00003 | $0.00101 |
Grade A, and why
prd 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.
This is a copy
100% identical to prd — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Requirements Document (PRD)
Overview
Design comprehensive, production-grade Product Requirements Documents (PRDs) that bridge the gap between business vision and technical execution. This skill works for modern software systems, ensuring that requirements are clearly defined.
When to Use
Use this skill when:
- Starting a new product or feature development cycle
- Translating a vague idea into a concrete technical specification
- Defining requirements for AI-powered features
- Stakeholders need a unified "source of truth" for project scope
- User asks to "write a PRD", "document requirements", or "plan a feature"
Operational Workflow
Phase 1: Discovery (The Interview)
Before writing a single line of the PRD, you MUST interrogate the user to fill knowledge gaps. Do not assume context.
Ask about:
- The Core Problem: Why are we building this now?
- Success Metrics: How do we know it worked?
- Constraints: Budget, tech stack, or deadline?
Phase 2: Analysis & Scoping
Synthesize the user's input. Identify dependencies and hidden complexities.
- Map out the User Flow.
- Define Non-Goals to protect the timeline.
Phase 3: Technical Drafting
Generate the document using the Strict PRD Schema below.
PRD Quality Standards
Requirements Quality
Use concrete, measurable criteria. Avoid "fast", "easy", or "intuitive".
# Vague (BAD)
- The search should be fast and return relevant results.
- The UI must look modern and be easy to use.
# Concrete (GOOD)
+ The search must return results within 200ms for a 10k record dataset.
+ The search algorithm must achieve >= 85% Precision@10 in benchmark evals.
+ The UI must follow the 'Vercel/Next.js' design system and achieve 100% Lighthouse Accessibility score.
Strict PRD Schema
You MUST follow this exact structure for the output:
1. Executive Summary
- Problem Statement: 1-2 sentences on the pain point.
- Proposed Solution: 1-2 sentences on the fix.
- Success Criteria: 3-5 measurable KPIs.
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 · 143 lines · 34 tokens per session scan A ed870a301af5
prd is a skill published in the GitHub repository thangchung/agent-engineering-experiment (27 stars, last pushed 5d ago), licensed MIT. It adds 34 tokens to every session and 1,007 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to prd, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
phoenix-cli-development
Design and implementation guide for the Phoenix CLI (px). Covers the noun-verb command structure, dual-audience design (humans and coding agents), Commander.js patterns, configuration resolution, output formats, exit codes, and conventions for adding or modifying commands. Triggers when working on phoenix-cli commands…
playground
Author, edit, or iterate on prompts in the Phoenix prompt playground, including running experiments over a dataset. Load before any playground ui. operation call, including single-shot prompt rewrites.
phoenix-graphql
Write efficient GraphQL queries against the Phoenix API. Load this skill in two cases: (1) before composing any non-trivial GraphQL query yourself for data analysis (via the phoenix-gql bash command) — it contains schema entrypoints and patterns that eliminate the need for introspection; (2) when the user asks for…
datasets
Understand what a Phoenix dataset is and reason well about its examples, outputs, splits, and how it feeds evaluators and experiments. Load this whenever a dataset is in view or the user asks what a dataset is, how splits work, what an output "means", or how datasets relate to experiments and evals. This skill governs…
evaluators
Author or refine a Phoenix evaluator — code or LLM-as-a-judge — that scores a run's output. Trigger when the user wants to create a new evaluator, improve an existing one's logic or rubric, choose labels, or decide what to measure on a dataset or experiment. Do NOT trigger on: (1) manual prompt drafting (use…
experiments
Run, read, and compare dataset-backed experiments to find evidence that a prompt or pipeline is improving. Trigger when the user wants to iterate over a dataset with experiments, compare experiment runs, read experiment quality/latency/cost, or decide whether a change actually helped. Running a prompt over a dataset…