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 mattgierhart/PRD-driven-context-engineering --skill prd-v06-architecture-designgit clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineeringWrote 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/mattgierhart/prd-driven-context-engineering/prd-v06-architecture-design)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v06-architecture-design"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v06-architecture-design/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/mattgierhart/prd-driven-context-engineering/prd-v06-architecture-design"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v06-architecture-design.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 | $0.00115 | $0.03455 |
| Opus 5 | $0.00057 | $0.01728 |
| Sonnet 5 | $0.00023 | $0.00691 |
| Haiku 4.5 | $0.00012 | $0.00346 |
Grade A, and why
prd-v06-architecture-design 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 — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Design
Position in workflow: v0.5 Technical Stack Selection → v0.6 Architecture Design → v0.6 Technical Specification
Architecture defines how your system components connect. This skill transforms stack selections into a coherent system design with explicit boundaries and integration patterns.
Consumes
This skill requires prior work from v0.3-v0.5:
- TECH-* technology decisions (from v0.5 Technical Stack Selection) — Tech choices become components; Build items become internal services, Buy/Integrate items become external connections
- RISK-* risk entries (from v0.5 Risk Discovery Interview) — High-priority RISK-* entries must have architectural mitigations; drives design decisions on failover, security, scaling
- FEA-* feature entries (from v0.3 Features Value Planning) — Features determine what components must be built; complex features may require distributed patterns
- ARC-* existing architecture decisions (from prior products if brownfield) — Inherited patterns constrain new designs (monolith with microservice, library reuse, auth pattern, etc.)
This skill assumes v0.5 Technical Stack Selection is complete with TECH- entries providing technology foundations.
Produces
This skill creates/updates:
- ARC-* entries (architecture decisions, status-based) — Decisions for structure, integration, security, performance, data, DevOps with rationale, alternatives considered, and consequences. No confidence scores; decisions have Status: Proposed/Accepted/Superseded
- System boundary diagram — Visual representation showing trust boundaries, components, and external integrations
- RISK-to-Architecture mapping — Validation showing every high-priority RISK-* has corresponding ARC-* mitigation or explicit acceptance
- Conformance rules (on ARC- entries) — for any decision that makes a structural claim ("X must not depend on Y", "all Z go through one adapter"), a machine-checkable rule. This turns the architecture into the expected topology (the blueprint graph) the v0.7 build is diffed against, and feeds the
architecture_conformancereadiness dimension. Seedocs/DEVELOPMENT_GRAPH.md.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 357 lines · 115 tokens per session scan A 6244b0ea8aa5
prd-v06-architecture-design is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 10d ago), licensed MIT. It adds 115 tokens to every session and 3,455 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 2026-08-30.
Other skills, from other repositories
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
architecture-patterns
Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use when architecting complex backend systems or refactoring existing applications for better maintainability.
moai-platform-deployment
Deployment and hosting platform specialist covering Vercel, Railway, and Convex. Use when deploying applications, configuring edge functions, setting up continuous deployment, or managing serverless infrastructure.
moai-platform-auth
Authentication and authorization specialist covering Auth0, Clerk, and Firebase Auth. Use when implementing authentication, MFA, SSO, passkeys, WebAuthn, social login, or security features.
loom-event-driven
Event-driven architecture patterns including message queues, pub/sub, event sourcing, CQRS, and sagas.
loom-background-jobs
Background job processing patterns including job queues, scheduled jobs, worker pools, retry strategies, and delivery guarantees.