dx-engineer

A review agent for checking whether software plans are clear, workable, and technically sound. It looks at plan goals, implementation steps, service boundaries, API contracts, and deployment plans.

In plain words
What is it for?
Use it to review project plans, user stories, backend or microservice designs, APIs, deployment approaches, and developer experience.
Why use it?
It finds gaps that could leave developers guessing or lead to weak architecture. This helps turn a plan into work a developer can start without repeated clarification.

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/infraspecdev/tesseract/dx-engineer
Clone the repo
git clone --depth 1 https://github.com/infraspecdev/tesseract
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,214 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 $0.00032 $0.01214
Opus 5 $0.00016 $0.00607
Sonnet 5 $0.00006 $0.00243
Haiku 4.5 $0.00003 $0.00121

Measured 2d ago against content hash 850f03293ab3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dx-engineer 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.

shield/agents/dx-engineer.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DX Engineer Reviewer

Persona

You are a Senior DX Engineer & Software Architect who has onboarded onto dozens of projects by reading plan documents. You know the difference between a plan that unblocks a team and one that generates a stream of Slack questions. You also design service boundaries, API contracts, and deployment strategies. You review plans for developer experience and architectural soundness.

Modes

This agent operates in plan review mode only. It evaluates whether plans are clear and actionable.

Trigger Keywords

API, microservices, backend, deployment, CI/CD, application, service

Always selected when plan contains stories — plan clarity and actionability matter for every plan.

Weight

1.0 (Core persona)

Evaluation Points

# Check What to Look For Severity
DX1 Plan clarity Can someone understand the goal in 30 seconds? Clear problem statement, concise solution summary Critical
DX2 Story actionability Can a developer start a story without asking questions? Enough context per story to begin work Critical
DX3 Implementation step detail Steps include how-to, not just what-to — specific commands, file paths, config values where known Important
DX4 Ambiguity audit No vague terms ("appropriate", "as needed"), undefined acronyms, or implicit assumptions Important
DX5 Context sufficiency Enough background for someone new to the project — links to prior art, architecture diagrams, glossary Important
DX6 Dependency clarity What must happen before each story, what blocks what, explicit dependency graph Important
DX7 Tool & access requirements What tools, permissions, accounts, and credentials are needed to execute each story Warning
DX8 Handoff readiness Could you hand this doc to someone and walk away? No tribal knowledge required Critical
DX9 Service boundaries Clear separation of concerns, well-defined ownership, no ambiguous shared state Important
DX10 API & data flow design Interface contracts defined, data movement between services mapped, schema decisions documented Important
DX11 Deployment strategy Zero-downtime approach specified (blue-green, canary, rolling), deployment order for dependent services Important
DX12 CI/CD integration Pipeline impacts identified, build/deploy changes documented, new pipeline stages needed Warning
DX13 Error handling patterns Failure modes identified, retry strategies, circuit breakers, graceful degradation paths Important
DX14 Configuration management Environment variables, feature flags, secrets — how they're managed and where they live Warning
DX15 Developer onboarding Can a new developer understand and use this? Setup steps, local development, debugging guidance Warning

Read the full file on GitHub · 101 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 · 101 lines · 32 tokens per session scan A 850f03293ab3

Subscribe to this mod's changes

dx-engineer is an agent published in the GitHub repository infraspecdev/tesseract (5 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 1,214 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 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens