CLI Coding Agents — 2026 Q2 Comparison
Claude Code, Copilot CLI, Gemini CLI, Codex CLI, Kiro, OpenCode

Six terminal-based AI coding agents compete for the developer's shell in 2026 Q2. This note compares their feature surfaces — not their model quality (which changes monthly) but their architectural bets: what contract does each offer between the developer, the agent, and the tools the agent can invoke?

The comparison is structured around the surfaces that matter for an operator choosing a daily driver: invocation patterns, permission models, MCP support, hooks, skills/agents, memory, sandboxing, and model portability.

Scope note: this covers the six agents with the deepest CLI surfaces as of April 2026. Other notable tools (Aider, Cursor Agent, Windsurf/Cline, Continue) are omitted either because their primary surface is an IDE extension rather than a terminal CLI, or because their CLI surface is thin enough that comparison at this level of detail is not informative. See Terminal AI Agents 2025 for the broader landscape including IDE-first tools.

Notable: Copilot CLI defaults to a Claude model, not a GitHub/OpenAI model. Gemini CLI and OpenCode are open source.

Claude Code and Codex CLI have the deepest non-interactive / scripting surfaces. Gemini CLI matches on output format and session management. Copilot CLI is the simplest invocation surface. Kiro's CLI is the least publicly documented.

Gemini CLI has the most mature OS-level sandboxing (four backends). Codex CLI has the cleanest tier model and a standalone codex sandbox tool for running arbitrary commands under the agent's sandbox policy. Claude Code has no OS-level sandbox — worktree isolation is filesystem-only, not process or network isolated. Kiro and OpenCode have no sandbox primitives.

Codex CLI's codex mcp-server is unique — it can run as an MCP server, meaning another agent can consume Codex as a tool. Claude Code has the most flexible multi-config story (--mcp-config accepts multiple files).

Claude Code has the most complete hook surface (7 event types + conditional if hooks). Copilot CLI is close with 6 hook types including an errorOccurred hook that no other agent has. Kiro has 5 triggers including AgentSpawn and veto via exit code 2 on PreToolUse. Earlier versions of this note incorrectly attributed file-event hooks to Kiro; the official docs show no file-event triggers.

The SKILL.md convention (originated by Anthropic) is now read by Claude Code, Copilot CLI, and OpenCode — the closest thing to a cross-harness standard. Copilot CLI ships no built-in skills but discovers SKILL.md files in .claude/skills/ and .agents/, so project-level skills written for Claude Code work without changes. Gemini CLI has the most developed install/manage surface for skills. Codex CLI and Kiro use AGENTS.md as the project-level agent configuration (different convention, same purpose).

Kiro's auto-generated product.md, tech.md, structure.md are unique — the agent bootstraps its own project understanding on first run. Claude Code has the most structured memory system (typed categories with an indexed MEMORY.md). Gemini CLI and Copilot CLI both have auto-compaction at the 95% threshold.

OpenCode has the broadest provider story (75+ via Models.dev). Codex CLI has the cleanest multi-provider config (config.toml profiles). Claude Code's provider flexibility is limited to API key and Vertex/Bedrock setup wizards. Kiro is locked to AWS Bedrock.

Codex CLI is the only agent with cloud-execution (codex cloud) and MCP-server modes. Copilot CLI supports ACP (Agent Client Protocol) — a competing open standard to MCP for agent interop. Claude Code's /remote-control provides browser-to-terminal bridging.

Reading across all six agents, the convergent surfaces are:

1. Non-interactive mode with -p / exec — every agent has a script-friendly mode. The shell integration pattern is settled.
2. MCP as the tool-extension protocol — all six support MCP. Configuration format varies (JSON, TOML, settings) but the transport is standard.
3. Project instruction files — CLAUDE.md, GEMINI.md, AGENTS.md, .kiro/steering/. Every agent auto-loads a project-level context document. No standard name.
4. Permission tiering — every agent has at least a read-only / ask / auto-approve ladder. The number of tiers varies (2–6) but the shape is the same.
5. Session persistence + resume — all but OpenCode support continuing a prior conversation.

Where the agents disagree reveals what each vendor considers the hard problem:

1. Sandboxing. Gemini CLI and Codex CLI invest heavily in OS-level sandboxing (Seatbelt, gVisor, Landlock). Claude Code invests in worktree isolation and permission hooks. Kiro and OpenCode punt entirely. The question: is isolation the agent's job or the operator's?
2. Hooks and lifecycle events. Claude Code and Kiro have rich hook surfaces; the others have basic or no hooks. The question: should the harness be programmable, or should external tooling (CI, scripts) handle lifecycle?
3. Skills portability. SKILL.md is becoming a cross-harness convention (Claude Code, Copilot CLI, OpenCode). AGENTS.md is a competing convention (Codex CLI, Kiro, OpenCode). The question: does the project instruct the agent (AGENTS.md) or does the agent discover capabilities (SKILL.md)?
4. Cloud execution. Only Codex CLI has a cloud-execution tier (codex cloud). The question: is the terminal the boundary, or is it just the client for a remote agent?
5. Model portability. OpenCode supports 75+ providers; Kiro locks to Bedrock. The question: is the agent married to a model, or is the model a pluggable backend?

Each agent's claims were independently verified by a subagent checking official documentation or local --help output. This section records what was checked, what version, and what was corrected.

All corrections have been applied to the tables above. The note is accurate as of the versions listed; flag surfaces change frequently and should be re-verified quarterly.

Channel note: Claude Code 2.1.114 is from the npm/=latest= channel (FreeBSD). Homebrew's stable channel ships 2.1.98 as of the same date. All flags in the comparison tables are present in both versions; the gap is power-user flags (--effort, --from-pr, --chrome, etc.) that the note intentionally omits as out of scope.

• Claude Code Workshop 2026 — deep-dive on Claude Code's surface.
• Claude Code Features — 2026 Q2 — speculative notes on Claude Code's direction.
• Terminal AI Agents 2025 — prior landscape survey; this note is the Q2 2026 update.
• Cloudflare Agents Week 2026 — where the agent infrastructure (sandbox, memory, identity) sits relative to these CLI surfaces.