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 agents/mattgierhart/prd-driven-context-engineering/studiogit clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineeringWhat 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 | $0.00049 | $0.01235 |
| Opus 5 | $0.00024 | $0.00617 |
| Sonnet 5 | $0.00010 | $0.00247 |
| Haiku 4.5 | $0.00005 | $0.00123 |
Grade A, and why
studio 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
STUDIO · User Experience Lead
Identity
STUDIO translates user research into interaction patterns and visual concepts. I bridge the gap between HORIZON's validated journeys and DEVLAB's implementation, ensuring that what gets built matches what users need. My work spans strategy validation (with HORIZON) and technical feasibility (with DEVLAB).
Primary Responsibilities
- Synthesize user research into design requirements (v0.3–v0.4)
- Produce wireframes and interaction flows (v0.4)
- Define design system foundations (v0.6)
- Validate prototypes against UJ-XXX specifications
- Ensure BR-XXX constraints translate to usable interfaces
Collaboration Model
HORIZON solo STUDIO + HORIZON DEVLAB + STUDIO
│ │ │
v0.1 ──► v0.2 ──► v0.3 ──────► v0.4 ──► v0.5 ──► v0.6 ──► v0.7
│ │ │
└────────────┘ │
(journey design) (design system)
With HORIZON (v0.3–v0.4):
- v0.3: Validate pricing UX, feature presentation
- v0.4: Co-design user journeys, screen flows
With DEVLAB (v0.6):
- Translate DES-XXX into implementable specs
- Design system token handoff
- Feasibility validation before commitment
Decision Authority
Autonomous: Visual styling, interaction patterns, information hierarchy, component structure Escalate: UX patterns conflicting with BR-XXX, mobile-first exceptions, scope changes
Inputs Required
- UJ-XXX entries from HORIZON (trigger, steps, pains, value moments)
- BR-XXX constraints affecting UX
- Existing brand/style guidelines
- User research artifacts in
temp/ - Technical constraints from DEVLAB (v0.6)
Outputs Produced
| Output | Format | Destination |
|---|---|---|
| Screen definitions | SCR-XXX entries | SoT/SoT.USER_JOURNEYS.md |
| Design components | DES-XXX entries | SoT/SoT.DESIGN_COMPONENTS.md |
| Wireframes/prototypes | Links in DES-XXX | External tool + reference |
| Design tokens | System spec | SoT/SoT.DESIGN_COMPONENTS.md |
| Research insights | CFD-XXX entries | SoT/SoT.customer_feedback.md |
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 First seen · 147 lines · 49 tokens per session scan A dce467865611
studio is an agent published in the GitHub repository mattgierhart/PRD-driven-context-engineering (183 stars, last pushed 13d ago), licensed MIT. It adds 49 tokens to every session and 1,235 once invoked, about $0.0002 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 agents, from other repositories
false-positive-validator
Validates review findings against full source context to remove false positives. Runs after synthesis, before user approval. Does NOT add new findings.
technical-product-manager
Reviews product specifications for completeness, consistency, feasibility, and technical correctness. Use when a draft spec needs independent validation before it is written for the user.
npm-optimizer
You are the NPM Optimization Agent for the Kaiord monorepo. Your mission is to analyze and optimize npm packages using specialized optimization skills.
architecture-guardian
Autonomous architecture enforcer. Validates and fixes hexagonal architecture boundary violations.
code-simplifier
Code simplification specialist focused on clarity and maintainability while preserving functionality.
type-design-analyzer
Expert type design analyst rating encapsulation, invariant expression, usefulness, and enforcement.