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-technical-specificationgit 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-technical-specification)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v06-technical-specification"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v06-technical-specification.svg" alt="Measured on agentmods" 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 | $0.00128 | $0.03441 |
| Opus 5 | $0.00064 | $0.01721 |
| Sonnet 5 | $0.00026 | $0.00688 |
| Haiku 4.5 | $0.00013 | $0.00344 |
Grade A, and why
prd-v06-technical-specification 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 8d 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 — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Specification
Position in workflow: v0.6 Architecture Design → v0.6 Technical Specification → v0.7 Build Execution
Technical specification defines the contracts developers build against: API endpoints and data models. This is the bridge between architecture and implementation.
Consumes
This skill requires prior work from v0.3-v0.6:
- ARC-* architecture decisions (from v0.6 Architecture Design) — System structure (monolith vs microservices) determines API organization; integration patterns guide webhook/adapter design
- TECH-* Build items (from v0.5 Technical Stack Selection) — Technologies chosen define data model types (PostgreSQL requires relational schema; MongoDB requires document schema)
- UJ-* user journeys (from v0.4 User Journey Mapping) — Journey steps determine API call sequences; value moments determine response contracts
- SCR-* screen entries (from v0.4 Screen Flow Definition) — Screen data requirements determine API response shape; form submissions map to POST/PUT/PATCH endpoints
- BR-* business rules (from v0.3 Commercial Model) — Business constraints enforced in API responses (rate limits, validation rules, field constraints)
This skill assumes v0.6 Architecture Design is complete with ARC- entries providing system structure.
Produces
This skill creates/updates:
- API-* entries (API endpoint contracts) — REST/GraphQL endpoint specifications with request/response shapes, auth requirements, error codes, tied to UJ-/SCR- consumers and DBT- data sources
- DBT-* entries (database schema contracts) — Data model specifications with fields, relationships, indexes, constraints, tied to API- accessors and BR- rules
- Screen-to-API validation matrix — Verification showing every SCR-* has supporting API-* and every UJ-* step can be completed via API calls
- API-to-Data validation matrix — Verification showing every API-* response field maps to DBT-* and every DBT-* is used by at least one API-*
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.
- 8d ago First seen · 374 lines · 128 tokens per session scan A 4a99c9ec0b04
prd-v06-technical-specification is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 7d ago), licensed MIT. It adds 128 tokens to every session and 3,441 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
loom-search
Full-text search and search engine implementation.
nuxthub
Use when building NuxtHub v0.10.6 applications - provides database (Drizzle ORM with sqlite/postgresql/mysql), KV storage, blob storage, and cache APIs. Covers configuration, schema definition, migrations, multi-cloud deployment (Cloudflare, Vercel), and the new hub:db, hub:kv, hub:blob virtual module imports.
api-baas-firebase
Firebase backend-as-a-service — Firestore, Authentication, Cloud Functions v2, Storage, Hosting, Admin SDK, security rules, emulator suite.
api-baas-neon
Serverless PostgreSQL with branching, autoscaling, and edge-compatible driver.
api-database-redis
Redis in-memory data store patterns with ioredis and node-redis -- caching, sessions, rate limiting, pub/sub, streams, queues, transactions, cluster.
api-baas-supabase
Supabase backend-as-a-service — Auth, Database, Realtime, Storage, Edge Functions, RLS policies, typed client.