Give it a bounded task
Turn “improve my site” into a job with a clear scope and finish line.
LEMON AGENT LEMON AGENT · a field guide to coding agents
You know how to chat with AI. Now learn how to work with one.
A coding agent can inspect a project, edit files, run commands, and check its work. This hands-on guide shows you how to give it a safe job, stay in control, and decide whether the result is actually right.
Start with the course if you are moving beyond chat. Use the field manual at any skill level when you want a sharper working system.
Already working with a coding agent? Skip ahead to the field manual and the watch-out lists.
What you will learn
A better working loop, not a magic prompt.
Stay involved without hovering
Know when the agent should inspect, plan, act, ask, or stop.
Make the system improve
Save corrections in project instructions, reusable skills, and small dependable tools.
Build leverage
Make every useful session improve the next one.
Let corrections survive the chat
Put project facts in AGENTS.md or CLAUDE.md. Package workflows as skills, with npx skills managing shared installs.
Prefer a clear tool surface
Use a CLI for direct local work, an API for service access, and MCP when a standard agent connection adds value.
Harvest small deterministic tools
Let code perform exact repeated operations while the agent handles judgment, orchestration, and glue.
Start here
Seven short lessons. One real workflow.
Each lesson gives you one idea, a decision to practice, and something you can paste into your own coding agent.
Open the 30-minute courseGo deeper
The field manual
Patterns from measured use, written for clarity without reducing the technical depth.
10 patterns
Working with Coding Agents
The core field guide: verification loops, design interviews, adversarial reviews, tool surfaces, small tools, and generated UIs. One pattern at a time, each with a prompt you can adapt.6 patterns
Shipping Software with Git + Coding Agents
How git and an agent compose: checkpoint commits, branches as blast radius, history the next session can read, diff-not-summary review, and recovery cheap enough to lean on.7 patterns
Keeping a Vault
A personal knowledge base an agent can actually work: plain files in a repo, directories as state, an inbox habit, a daily log, and a doctor script keeping it honest.1 pattern
What Does AI Say About You?
Assistants answering buyer-intent questions are a front door to your work. A stable-ID prompt battery, an isolated web-enabled harness, and a graded findings table measure what they say today — and whether your fixes moved it.5 patterns
Paying for Things with Agents
Fund an agent so it can pay for what it uses: four funding routes compared, the five ways to lose the money, per-call and per-day spend caps, and one real sub-cent purchase you can read back on-chain.Services agents can call
Five live endpoints, priced per call.
Paid over x402. Prices verified 2026-09-02.
Toolshed 19 hosted format converters, one call per conversion. $0.002-$0.006/call
https://toolshed.lemon-agent.dev 10x402 x402 conformance linting, 82 checks per report. $0.005-$0.25/call https://10x402.com kino402 Frontier video and TTS generation, one call per render. $0.008-$0.372/call https://kino402.com penny402 Ten muse and oracle attractions, one flat price per call. $0.0025/call https://penny402.fun Parallax Settlement-graph market facts about the x402 economy. $0.010/call https://parallax402.com Experiments: Lemon Agent also houses small tools and agent-facing services. The first, pathgrip, is a bookmark store agents can call. It runs as the operator’s own instance today; there is nothing for you to sign up for yet, and we’d rather say so than pretend. See its current status →