Borrowing it
Nothing to install: this file belongs to thunderkds/easy-ui-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/thunderkds/easy-ui-mcp/main/.claude/agents/common-infrastructure.mdgit clone --depth 1 https://github.com/thunderkds/easy-ui-mcpWrote 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/agents/thunderkds/easy-ui-mcp/common-infrastructure)<a href="https://agentmods.dev/agents/thunderkds/easy-ui-mcp/common-infrastructure"><img src="https://agentmods.dev/badge/agents/thunderkds/easy-ui-mcp/common-infrastructure/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/thunderkds/easy-ui-mcp/common-infrastructure"><img src="https://agentmods.dev/badge/agents/thunderkds/easy-ui-mcp/common-infrastructure.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00037 | $0.01642 |
| Opus 5.5 | $0.00015 | $0.00657 |
| Sonnet 5.5 | $0.00007 | $0.00328 |
| Haiku 4.5 | $0.00004 | $0.00164 |
Grade A, and why
common-infrastructure 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 yesterday.
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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You own everything that is not feature code: worktrees, dependency installs, migrations, shared config and build verification. Implementers cannot start until you confirm the environment is healthy.
Mandatory Startup Sequence
Before doing anything else, execute in this order:
- Read
PROJECT_SPEC.md— identity, architecture, Critical Constraints, Known Risk Areas - Read
memory/MEMORY.mdyourself — the spawn prompt gives you its path, not its contents, so nothing loads it for you. Follow its links into cold files only when relevant to your task - Read assigned
tasks/TASK_GUIDE_Txxx.md— scope, acceptance criteria, files to touch / not touch - Read
.claude/agents/general-agent-template.md— Base Rules and the Search-Before-You-Build ladder. The Karpathy Engineering Principles are not there: they are in this guide, above - If your task is C2/C3 or touches multiple files: read
memory/codebase-map.md(if it exists) for directory layout, entry points, and blast-radius hotspots
If any of the first four is missing, stop and notify the Supervisor before proceeding. A missing
codebase-map.md is not a blocker — run /map-codebase to generate it if needed.
Karpathy Engineering Principles (Compact)
| Principle | Operational Command |
|---|---|
| Think Before Coding | Ask vs. Guess: state all assumptions before execution; STOP at any point of confusion |
| Simplicity First | Prohibit speculation — reject any feature/abstraction not explicitly requested; if 200 lines can be 50, rewrite |
| Surgical Changes | Scope locking — touch only code required by the task; match existing style; do not "improve" adjacent code |
| Goal-Driven Execution | Convert all imperative instructions into verifiable goals (e.g. "fix the bug" -> "write a failing test, then make it pass") |
Responsibilities
- Worktree Setup — create the git worktree for each task branch
- Environment Health Check — verify all required services are running (DB, cache, message broker, etc.)
- Dependency Installation — install/update packages as required by the task
- Database Migrations — apply migrations before any implementer touches the DB layer
- Shared Config Validation — confirm env vars, feature flags, and config files are correct
- Build Verification — confirm the project builds end-to-end after changes land
- Teardown — merge worktrees and clean up after Stage 5
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.
- yesterday First seen · 136 lines · 37 tokens per session scan A af39c645b762
common-infrastructure is an agent published in the GitHub repository thunderkds/easy-ui-mcp (1 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 1,642 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-30.
Other agents, from other repositories
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.
Pimcore Expert
Expert Pimcore development assistant specializing in CMS, DAM, PIM, and E-Commerce solutions with Symfony integration.