Overview

These guides compare AI coding CLIs along concept lines, not tool lines. Pick a concept, see how it works in each tool side by side. Tab selections sync across pages - pick “Claude Code” once and every chapter opens to that tab.

If you’re new to how AI coding agents actually work - the loop, the context window, why sessions are independent - start with How agents work. It’s the shared substrate every chapter below assumes.

The translation table below now runs six tools wide. This section started with three terminal CLIs - Claude Code, Codex, and OpenCode - and every chapter still goes deepest on those three; Cursor, Copilot, and Pi have since been folded into the comparison too, since the same concepts apply there (with real gaps, called out honestly where a tool has no equivalent).

The six tools anchoring the translation table:

• Claude Code - Anthropic
• Codex CLI - OpenAI
• OpenCode - SST (open source)
• Cursor - Cursor, IDE + CLI
• Copilot - GitHub, primarily via VS Code
• Pi - Earendil / minimal harness

Find the right primitive

Fourteen chapters is a lot of doors. If you already know the problem you’re trying to solve, start from the problem:

Step 1 of 2: pick the kind of problem.

Where’s it going wrong?

It doesn’t know how we workfacts · procedures · saved promptsIt won’t stay in its lanegates · guardrails · approvalI’m still the bottleneckreach systems · run unattended · ship to teamIt burns window and moneyisolation · cheaper models · window hygieneI can’t tell how any of this is wiredthe loop · config precedence · what loads when

Say the problem, get the primitive. Pick the complaint that sounds like yours.

The translation table

Every row links to the chapter for that concept. Cells show the tool’s term for the same idea - or - if it has no equivalent.

Concept	Claude Code	Codex	OpenCode	Cursor	Copilot	Pi
Rules	CLAUDE.md, .claude/rules/	AGENTS.md	AGENTS.md	.cursor/rules/*.mdc or AGENTS.md	.github/copilot-instructions.md or AGENTS.md	AGENTS.md / CLAUDE.md + ~/.pi/agent/
Subagents	Subagents, Agent teams (exp.)	Subagents	general / explore / scout + custom	Auto-delegation, /name, or mention	Custom agents, spawned via runSubagent	- (extension/package, or a second pi process)
Model selection	/model (Anthropic only)	/model, --model (OpenAI)	Per-agent, multi-provider	Per-chat picker, multi-provider	Per-chat picker, plan-gated roster	/model, 15+ providers via models.json
Slash commands	Bundled + skill-invocable	Built-in + ~/.codex/prompts/ (deprecated → skills)	commands/	.cursor/commands/	.github/prompts/*.prompt.md	Built-ins + /skill:name + prompt templates
Skills	Skills (SKILL.md)	Skills (SKILL.md)	.opencode/skills/	.cursor/skills/	.github/skills/	SKILL.md in .pi/skills/ + .agents/skills/
MCP servers	.mcp.json, /mcp	config.toml, can also be an MCP server	Configurable	.cursor/mcp.json	.vscode/mcp.json	- (no native MCP, by design)
Hooks	Lifecycle hooks in settings.json	Lifecycle scripts	Plugin hooks (JS/TS)	hooks.json, 21+ events	Per-surface hook files	TypeScript extensions (ExtensionAPI)
Permissions & sandboxing	Allow/ask/deny + managed policy	Sandbox tiers + approval policy	Per-tool, per-agent	Auto-run mode + allow/denylist	Per-call approval + auto-approve	No prompts (YOLO default); container/extension gates
Plan mode	Shift-Tab cycle (4 modes)	Permission/sandbox posture (untrusted + read-only)	plan primary agent	First-class IDE mode	Mode dropdown (Plan agent)	- (file a plan, or extension/package)
Configuration	settings.json (layered)	config.toml + named profiles	opencode.json	VS Code settings.json + .cursor/	VS Code settings.json + .github/	~/.pi/agent/settings.json + .pi/settings.json (deep-merge)
Context window management	/context, /compact, /clear	/status, /compact, /new	Auto-compaction on overflow, --continue	/summarize, New Chat	/compact, chat context control	Auto-compaction + /tree session tree
Headless / CI	claude -p	codex exec	opencode run	cursor-agent -p	copilot --prompt	pi -p, --mode json, RPC, SDK
Plugins & marketplaces	Plugins + marketplaces	Plugins (skills + apps + MCP + hooks)	JS/TS plugins	- (VS Code extensions + MCP Marketplace)	Extensions + plugins (preview)	Pi packages (pi install npm:… / git:…)

How to read these guides

Four things are in the same place on every chapter, so you can navigate by landmark:

• A scenario up top - the concrete problem the primitive exists to solve, before any definition.
• How it works in each tool - a tabbed block with one tab per tool: real paths, real syntax, the gotchas that bite.
• Comparison - a table summarising where the tools actually diverge.
• Upstream references - a link to each tool’s canonical doc, because these ship fast and this page doesn’t.

Everything between the scenario and the tabs is chosen per concept, not per template. Structural ideas get a diagram; ones that only make sense in sequence get a worked example; ones where the tools diverge on capability get a decision table. If a chapter skips a device, that’s a judgement about the concept, not an omission.

Most chapters also carry an interactive widget near the top - something to poke at rather than read. They’re built to make one decision concrete, not to decorate the page.

A note on name collisions

The same word can mean different things across these tools. The chapters call these out individually, but a few are worth flagging up front:

• “Agents” - OpenCode has primary agents (build, plan); Claude Code has Agent teams (independent peer sessions, experimental); Copilot has custom agents (.agent.md, both a chat persona and a delegable subagent). Most tools also have in-session subagents - Pi doesn’t, by design. Separately, Cursor Cloud Agents and the Copilot Coding Agent are async remote sandboxes that return a PR, closer to a hand-off than an in-session subagent. Always qualify which kind.
• “Plan mode” - a Claude Code Shift-Tab mode cycle, an OpenCode primary agent, a Codex sandbox + approval combo, and a first-class IDE mode with its own picker entry in Cursor and Copilot. Pi has none (you file a plan or reach for an extension). Same posture, many implementations.
• “Hooks” - first-class lifecycle handlers in Claude Code, Codex, and Cursor; in OpenCode they’re registered from inside JS/TS plugins; Pi has no declarative hooks (you write TypeScript extensions instead). Copilot’s copilot-setup-steps.yml is not a runtime hook - it’s a one-time sandbox-prep GitHub Actions workflow.
• AGENTS.md is a real shared standard. Codex, OpenCode, Cursor, Copilot, and Pi all read it natively (Pi and Copilot also read CLAUDE.md directly). Claude Code reads CLAUDE.md, but you can import @AGENTS.md for one source of truth across every tool in scope.