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 agentmods add skills/mattgierhart/prd-driven-context-engineering/prd-v05-technical-stack-selectionnpx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v05-technical-stack-selectiongit 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-v05-technical-stack-selection)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v05-technical-stack-selection"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v05-technical-stack-selection.svg" alt="Measured on agentmods" 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 | $0.00151 | $0.04465 |
| Opus 5 | $0.00076 | $0.02233 |
| Sonnet 5 | $0.00030 | $0.00893 |
| Haiku 4.5 | $0.00015 | $0.00447 |
Grade A, and why
prd-v05-technical-stack-selection 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 5d 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 — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Stack Selection
Make technology decisions for every capability your product needs — starting with what you already have, then evaluating what fits, then deciding what to build.
Position in workflow: v0.5 Risk Discovery Interview → v0.5 Technical Stack Selection → v0.6 Architecture Design
Consumes
This skill requires prior work from v0.3-v0.5:
- FEA-* feature entries (from v0.3 Features Value Planning) — Every feature translates to technical capability requirements; derives which capability areas need technology decisions
- SCR-* screen entries (from v0.4 Screen Flow Definition) — Screen count and component complexity informs frontend technology needs; DES- components reveal design system constraints
- RISK-* risk entries (from v0.5 Risk Discovery Interview) — RISK- constraints directly affect technology choices (RISK-003: latency → choose edge hosting; RISK-004: compliance → choose HIPAA-ready provider)
- Existing TECH-* entries (from prior products if brownfield) — If product family exists, inherited technology decisions constrain new choices
- Product family information (from user discovery if brownfield) — Shared infrastructure, existing databases, established frameworks narrow the evaluation space
This skill assumes v0.5 Risk Discovery Interview is complete and FEA-/SCR-/RISK- entries provide the constraint foundation.
Produces
This skill creates/updates:
- TECH-* entries (technology decisions, decision type + rationale) — Decisions for each capability area with categories (Reuse/Extend/New/Replace), options considered, choice made, and rationale tied to FEA-/RISK- constraints
- Risk-to-Technology mapping table — Validation showing every RISK- entry has corresponding TECH- response or explicit acceptance
- Technical feasibility artifact — Confidence assessment on whether technology choices support feature MVP-SCOPE and risk mitigations
All TECH- entries should include:
- Decision Category: Reuse/Extend/New/Replace/Build/Buy/Integrate/Research
- Features Served: FEA-XXX references (every TECH- must serve at least one feature)
- Risk Constraints: RISK-XXX references (if any risks constrain this decision)
- Rationale: Why this choice; trade-offs considered
- Cost Assessment: Current stage cost AND 10x scale cost for Buy decisions (MVP stage: prioritize speed and quality, not optimization)
What ships with it
5 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.
- 5d ago First seen · 384 lines · 151 tokens per session scan A e401cbeac06d
prd-v05-technical-stack-selection is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 4d ago), licensed MIT. It adds 151 tokens to every session and 4,465 once invoked, about $0.0008 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
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.
nw-ddd-eventsourcing
Event Sourcing and CQRS as DDD implementation patterns — when to use, aggregate event streams, projections, snapshots, sagas, upcasting, conflict resolution.