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 umangbuilds/dhurandhar-os --skill prd-writergit clone --depth 1 https://github.com/umangbuilds/dhurandhar-osWrote 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/umangbuilds/dhurandhar-os/prd-writer)<a href="https://agentmods.dev/skills/umangbuilds/dhurandhar-os/prd-writer"><img src="https://agentmods.dev/badge/skills/umangbuilds/dhurandhar-os/prd-writer/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/umangbuilds/dhurandhar-os/prd-writer"><img src="https://agentmods.dev/badge/skills/umangbuilds/dhurandhar-os/prd-writer.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 | $0.00110 | $0.02862 |
| Opus 5 | $0.00055 | $0.01431 |
| Sonnet 5 | $0.00022 | $0.00572 |
| Haiku 4.5 | $0.00011 | $0.00286 |
Grade A, and why
prd-writer 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 11d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Writer
PRD Writer is the spec layer. The operator says "spec out the merchant disbursement flow" — PRD Writer does not write code, does not ship anything. It writes the spec and refuses to lock it until the failure modes, money flow, and consent capture have been named.
A locked spec saves the engineer 4 hours a day. An unlocked spec costs the operator a month.
When this skill activates
Auto-trigger conditions:
- "Spec," "PRD," "let's design," "requirements," "scope this," "write the spec," "lock the spec," "let's nail the requirements."
- Operator describes a feature in terms of user behaviour rather than implementation.
Explicit invocation: "use prd-writer to spec X."
Does not activate on: code generation (Builder), security review (Reviewer), brainstorming the idea itself (Idea Reality Check).
Hands off to: Builder (once the spec is locked) and/or Reviewer (when reviewing an existing PRD).
Section structure (mandatory)
Every PRD has these sections, in this order:
- Title — short, descriptive. Not a feature title; a behaviour title. ("Merchant disbursement, T+1 settlement" not "DisburseService.")
- Goal — one sentence. What the user does after this ships that they cannot do today.
- Non-goals — list. What this spec deliberately does NOT do. Critical for scope discipline.
- User journey — step-by-step. From first touch to outcome.
- Acceptance criteria — bulleted, testable conditions. Each criterion is a Given-When-Then or equivalent.
- Money flow diagram (if money is involved) — text or ASCII diagram showing every account, every transition, every fee.
- Reconciliation ownership (if money is involved) — who owns the books when our records and the PSP's records disagree.
- Failure modes — explicit list of what can break. Each has a handling line.
- Regulatory triggers — checklist. Personal data Y/N. Lending / credit Y/N. Cross-border data Y/N. GST/TDS impact Y/N. Each Y triggers a routing line.
- Test plan — categories of tests required (unit, integration, contract, end-to-end, load if applicable). Specific scenarios.
- Open questions — items pending operator decision. The spec is not locked until this list is empty.
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.
- 11d ago First seen · 222 lines · 110 tokens per session scan A 4abc67a07d30
prd-writer is a skill published in the GitHub repository umangbuilds/dhurandhar-os (1 stars, last pushed 4mo ago), licensed MIT. It adds 110 tokens to every session and 2,862 once invoked, about $0.0006 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 2026-08-31.
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…