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 roedyrustam/vibes-plug --skill prd-architectgit clone --depth 1 https://github.com/roedyrustam/vibes-plugWrote 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/roedyrustam/vibes-plug/prd-architect)<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/prd-architect"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/prd-architect/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/roedyrustam/vibes-plug/prd-architect"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/prd-architect.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 | $0.00058 | $0.04540 |
| Opus 5.5 | $0.00023 | $0.01816 |
| Sonnet 5.5 | $0.00012 | $0.00908 |
| Haiku 4.5 | $0.00006 | $0.00454 |
Grade A, and why
prd-architect 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 2d 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 — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Architect & Documentation Lifecycle (2026 Edition)
English
Orchestration & Integration
- Upstream Orchestrators: Works under
brainstormingandzero-to-prod-orchestrator(Phase 1 - Discovery & PRD, and Phase 8 - Docs Handoff) as the primary specification guardrail. - Downstream Cooperating Skills:
spec-driven-development-expert— Convert PRD requirements into executable OpenAPI and TypeSpec contracts.domain-driven-design-expert— Model domain bounded contexts and ubiquitous language in PRD sections.session-memory-manager— Ground session memory on approved PRD/ERD specifications and ADR records.anti-slop— Enforce concrete DDL schemas, verifiable NFR targets, and zero marketing buzzwords.production-ready-hardener— Audit documentation completeness before final release.
Description
A mandatory lifecycle guardrail covering two distinct phases:
- Phase 1 (Pre-Code): Enforces creating a comprehensive Product Requirements Document (PRD), ERD, and general Documentation before generating code. Introduces PRD-as-Code — machine-readable and version-controlled.
- Phase 2 (Post-Code / Maintenance): Automatically maintains project documentation after every successful build or feature implementation, updating
CHANGELOG.md,BLUEPRINT.md,PROGRESS.md, and Architecture Decision Records (ADRs).
Trigger Conditions
- Phase 1: User requests building a new app/SaaS/feature from scratch; no existing PRD/blueprint; unclear scope.
- Phase 2: A feature, bug fix, or refactor is successfully implemented; user asks to "update docs" or "save progress"; a significant architectural decision is made; milestone completion.
Phase 1: Pre-Code Requirements & Enforcement
Why PRD Before Code: Prevents scope creep, aligns AI output, enables traceability, reduces rework, version-controlled.
Enforcement Protocol
- Detect: When user requests a new project build.
- Pause: Do NOT generate any code.
- Generate Assets (Zero-Slop Standard): Automatically draft
PRD.md,ERD.md,DOCUMENTATION.md, andROADMAP.md(orPROGRESS.md). Enforceanti-slop: zero marketing buzzwords; mandate concrete PostgreSQL DDL schemas, explicit REST/RPC contracts, and verified latency NFR budgets. - Review: Present to user for approval/edits.
- Confirm: Proceed to code generation ONLY after approval.
- Reference: Cite these documents in all subsequent decisions.
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.
- 2d ago Changed · +11 lines · +58 tokens per session af14966733eb
- 3d ago Changed · +2 lines · -58 tokens per session 4a6aaf18dbff
- 6d ago Changed · +145 lines 105ff39bdcea
- 15d ago Changed 115888665e29
- 20d ago Changed 7baf24d20405
- 21d ago Changed b335cfc87276
- 23d ago Changed · -6 lines · +48 tokens per session e04d50a658cb
- 25d ago Changed · +6 lines · -48 tokens per session 542988d80da4
- 1mo ago Changed 2fc6db11bbb1
- 1mo ago First seen · 183 lines · 58 tokens per session scan A 139a8bacc507
prd-architect is a skill published in the GitHub repository roedyrustam/vibes-plug (113 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 4,540 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
pptx
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks.
docx
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4)…
ai-engineering-toolkit
Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
ai-prompt-regression-testing
Use when comparing prompt changes against a fixed evaluation set: record actual model settings, required checks, missing results, judge limitations and case-level regression evidence.
mantis-report
Generates a human-readable security review packet compiled from confirmed findings and exploit chains. Use at the end of a review cycle to produce stakeholder-facing documentation. Don't use for auditing code or verifying patches directly.