01 / Tools

Open-source CLIs, templates, and setup packets.

Built on the operating floor, shipped when ready, and preserved through existing drop URLs.

#010/Mini-Agents/Prototype

Mini-Agent: Daily Newsletter Packer

Bundle daily intel into a ready-to-send newsletter pack.

Open latest drop

02 / Shelf

15 public drops as usable proof-stock.

The Tools surface reframes drops for humans while keeping /drops/[slug] as the stable detail contract.

#010Mini-AgentsPrototype

Mini-Agent: Daily Newsletter Packer

Bundle daily intel into a ready-to-send newsletter pack.

Operator command
starkslab drops open mini-agent-daily-newsletter-packer
#009RecipesStable

Deployment Recipe (Vercel/Railway)

Deploy agent systems quickly with consistent infra decisions.

Operator command
starkslab drops open deployment-recipe-vercel-railway
#008ToolingStable

Evaluation Runner Template

Automate eval suites to keep agents in spec.

Operator command
starkslab drops open evaluation-runner-template
#007PrinciplesExperimental

Sandbox Execution Pattern

Run unsafe actions inside controlled execution sandboxes.

Operator command
starkslab drops open sandbox-execution-pattern
#006PrinciplesStable

Tool Registry Pattern

Prevent tool sprawl by enforcing a registry contract.

Operator command
starkslab drops open tool-registry-pattern
#005ToolsExperimental

Claude Agent Workspace (Anthropic Agent SDK)

You want a real agent workspace — not a chat tab. Something multi-workspace, tool-enabled, with files, repeatable runs, and BYOK keys per workspace — so you can build and ship agent workflows without duct-taping scripts together.

Operator command
starkslab drops open claudeagentsdk
#005BlueprintsStable

Artifact Streaming -> UI Contract

Keep streaming artifacts aligned with UI expectations.

Operator command
starkslab drops open artifact-streaming-ui-contract
#004CLI ToolsStable

trustmrr-cli

You need verified startup revenue data — MRR, growth, churn, customer counts — but TrustMRR only has a web UI. No way to query it from your terminal or pipe it into agent workflows.

Operator command
starkslab drops open trustmrr-cli
#004RecipesExperimental

Objective Dispatcher Pattern

Route tasks across agents while preserving the core objective.

Operator command
starkslab drops open objective-dispatcher-pattern
#003CLI ToolsStable

datafast-cli

DataFast has a clean analytics API, but there's no CLI. You can't check your site stats from the terminal, pipe them to scripts, or hand them to an AI agent as a tool. You're stuck in a browser dashboard.

Operator command
starkslab drops open datafast-cli
#003ToolingStable

MCP Starter Template

Launch an MCP server quickly with sane defaults.

Operator command
starkslab drops open mcp-starter-template
#002FrameworksExperimental

Minimal Agent Framework (MAF)

Every AI agent framework is a maze of abstractions. You can't trace what happened, you can't replay a failed run, and when something breaks you're debugging the framework instead of your agent. You need something you can actually read.

Operator command
starkslab drops open minimal-agent-framework
#002Prototype ZoneExperimental

Telegram Multimodal Normalizer

Normalize mixed Telegram inputs into structured, reliable payloads.

Operator command
starkslab drops open telegram-multimodal-normalizer
#001ToolsStable

X Scheduler on Railway

Your AI agent needs to post to X on a schedule — without paying for bloated tools or losing control.

Operator command
starkslab drops open x-scheduler-railway
#001BlueprintsStable

LangGraph Production Agent Template

Ship a LangGraph agent stack without reinventing core patterns.

Operator command
starkslab drops open langgraph-production-agent-template

Looking for paid toolkits?

Public drops prove the work. Products package the deeper setup, docs, and operating loops.

See Products