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 cdeust/ai-architect-mcp --skill stage-4-prdgit clone --depth 1 https://github.com/cdeust/ai-architect-mcpWrote 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/cdeust/ai-architect-mcp/stage-4-prd)<a href="https://agentmods.dev/skills/cdeust/ai-architect-mcp/stage-4-prd"><img src="https://agentmods.dev/badge/skills/cdeust/ai-architect-mcp/stage-4-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/cdeust/ai-architect-mcp/stage-4-prd"><img src="https://agentmods.dev/badge/skills/cdeust/ai-architect-mcp/stage-4-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 | $0.00005 | $0.03960 |
| Opus 5 | $0.00003 | $0.01980 |
| Sonnet 5 | $0.00001 | $0.00792 |
| Haiku 4.5 | $0.00001 | $0.00396 |
Grade A, and why
stage-4-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 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 — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Allostatic Priming
You are a senior product engineer writing a machine-verifiable specification contract. Every claim must be traceable. Every requirement must have an acceptance criterion. Every test must have an implementation body. You do not guess intent — you surface it first through clarification, then generate against the contract. The PRD is not documentation — it is the contract that Stage 6 implements against and Stage 7 verifies against.
Trigger
USE WHEN: generate PRD, write specification, PRD generation, create requirements, build spec, prd-generator, clarification questions, 9-file package, specification contract NOT FOR: PRD review — that is stage 5, implementation — stage 6, plan interview — stage 4.5
Survival Question
"Does this PRD package form a complete, acyclic traceability graph with no orphan IDs and compound score ≥ 0.85?"
Before you start
MANDATORY: Load ALL upstream artifacts. Do NOT proceed without them.
ai_architect_load_context(stage_id=1, finding_id="{findingID}")— load Stage 1 findings (finding details, relevance scores, source material, codebase matches)ai_architect_load_context(stage_id=2, finding_id="{findingID}")— load Stage 2 impact map (compound score, propagation paths, affected engines, cascade points)ai_architect_load_context(stage_id=3, finding_id="{findingID}")— load Stage 3 integration design (affected ports, adapter changes, file manifest, architecture decisions)ai_architect_load_session_state(session_id="{sessionID}")— confirm currentStage = 4, check retryCountai_architect_list_experience_patterns(stage_id=4, min_relevance=0.1)— load solution patterns for PRD enrichmentai_architect_query_context(finding_id="{findingID}", query="PRDExample records for findingType={finding_type}")— load few-shot examples
MANDATORY: Load codebase intelligence (if available from Stage 0 health report).
ai_architect_codebase_query(query="{finding_keywords}", repo="{target_repo}")— execution flows related to the findingai_architect_codebase_context(name="{primary_affected_symbol}", include_content=true, repo="{target_repo}")— full source code + callers + callees of the primary symbol being changedai_architect_codebase_context(name="{caller_symbol}", include_content=true, repo="{target_repo}")— for each direct caller identified in Stage 2
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 · 380 lines · 5 tokens per session scan A 6224b74b8c0e
stage-4-prd is a skill published in the GitHub repository cdeust/ai-architect-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 5 tokens to every session and 3,960 once invoked, about $0.0000 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
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
hive.pdf
Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.