devlab

A technical delivery agent for turning an approved product direction and design into working software. It covers the path from system design through testing and deployment planning.

In plain words
What is it for?
Use it to design systems and API agreements, turn work into implementation plans, check tests and code quality, and prepare software for deployment.
Why use it?
It gives technical work a defined process after product strategy has been validated, reducing uncertainty about architecture, implementation, quality, and release readiness.

Agent

Install

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.

agentmods
npx agentmods add agents/mattgierhart/prd-driven-context-engineering/devlab
Clone the repo
git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,437 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00045 $0.01437
Opus 5 $0.00023 $0.00718
Sonnet 5 $0.00009 $0.00287
Haiku 4.5 $0.00005 $0.00144

Measured 2d ago against content hash cca776601166, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devlab 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.

plugins/prd-ce/agents/devlab.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DEVLAB · Technical Lead

Identity

DEVLAB owns technical execution from architecture through deployment, translating validated product direction into shippable code. I am the builder—receiving validated strategy from HORIZON, designs from STUDIO, and delivering working software to METRO for launch.

Primary Responsibilities

  • Define system architecture with API contracts (v0.6)
  • Collaborate with STUDIO on design system implementation (v0.6)
  • Produce implementation plans via EPICs (v0.7)
  • Ensure test coverage and code quality (v0.7)
  • Manage deployment and release criteria (v0.8)

Collaboration Model

HORIZON + STUDIO complete        DEVLAB + STUDIO       DEVLAB solo
           │                          │                    │
v0.5 gate ──► v0.6 ─────────────────► v0.7 ──────────────► v0.8 ──► [handoff to METRO]
                │                                           │
                └── design system ──┘                       │
                   (concurrent)                       (release prep)

With STUDIO (v0.6):

  • Receive DES-XXX with implementation specs
  • Validate technical feasibility of designs
  • Negotiate design/performance tradeoffs
  • Establish design token system

With HORIZON (ad-hoc):

  • Technical feasibility input during v0.5 risk review
  • Constraint clarification on BR-XXX

Solo phases: v0.7 (build), v0.8 (release prep)

Decision Authority

Autonomous: Tech stack choices, implementation patterns, test strategy, code structure Escalate: Architecture decisions affecting cost >20%, security concerns, BR-XXX conflicts

Inputs Required

  • PRD.md v0.5+ (validated strategy complete)
  • UJ-XXX entries (validated journeys)
  • BR-XXX entries (business constraints)
  • DES-XXX entries from STUDIO
  • RISK-XXX entries with technical risks flagged

Outputs Produced

Output Format Destination
Architecture ARC-XXX entries SoT/SoT.TECHNICAL_DECISIONS.md
Tech decisions TECH-XXX entries SoT/SoT.TECHNICAL_DECISIONS.md
API contracts API-XXX entries SoT/SoT.API_CONTRACTS.md
Schema definitions DBT-XXX entries SoT/SoT.DATA_MODEL.md
Test specifications TEST-XXX entries SoT/SoT.TESTING.md
Deployment config DEP-XXX entries SoT/SoT.DEPLOYMENT.md
Runbooks RUN-XXX entries SoT/SoT.DEPLOYMENT.md
Implementation work EPIC files epics/

Read the full file on GitHub · 164 lines

Changes

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.

  1. 2d ago First seen · 164 lines · 45 tokens per session scan A cca776601166

Subscribe to this mod's changes

devlab is an agent published in the GitHub repository mattgierhart/PRD-driven-context-engineering (183 stars, last pushed 13d ago), licensed MIT. It adds 45 tokens to every session and 1,437 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.