Agent Support

Connect Smithers to the coding agent you already use (Claude Code, Codex, Cursor, Copilot, Pi, Hermes, OpenClaw, and ~20 more) so the agent can run, watch, and steer workflows for you.

Smithers is driven by an agent, not clicked by a human. You ask your coding agent for an outcome, “implement rate limiting and keep iterating until the tests pass”, and it reaches for Smithers, starts the workflow, watches it, and clears approvals on your behalf. These pages cover how to wire Smithers into each agent so it can do that.

Just want to get running? Set up in your harness is the two-minute version, with a copy-paste prompt that has your agent install Smithers for you.

There are three integration surfaces. Most agents support more than one; pick the one that matches how the agent is extended.

Surface	What it gives the agent	Ship it with
Skill	Fluency in Smithers (when to use it, the CLI verbs, the component catalog) loaded on demand	skills add
MCP server	Structured tools to list, run, watch, inspect, and control runs without shell-parsing	mcp add or native MCP config
Instructions	A standing note in AGENTS.md / CLAUDE.md so the agent knows Smithers is available	a few lines in the repo

Two commands cover most agents

The Smithers CLI installs both the skill and the MCP server into every coding agent it detects on your machine, no per-agent config by hand.

# Install the Smithers skill set into every detected agent
# (Claude Code, Codex, Cursor, Copilot, Gemini, OpenCode, Amp, Windsurf, …)
bunx smithers-orchestrator skills add

# Register Smithers as an MCP server in every detected agent
bunx smithers-orchestrator mcp add

Target a single agent with --agent, or scope to the current project with --no-global:

bunx smithers-orchestrator mcp add --agent cursor
bunx smithers-orchestrator skills add --no-global   # writes .agents/skills in the repo

skills add generates a skill per CLI command group (bunx smithers-orchestrator up, bunx smithers-orchestrator ps, bunx smithers-orchestrator approve, …) and installs them to the canonical ~/.agents/skills directory, symlinking into each agent that uses its own path (Claude Code → ~/.claude/skills, Windsurf → ~/.codeium/windsurf/skills, …). mcp add registers bunx smithers-orchestrator --mcp in each agent’s MCP config. Override the launch command with --command if Smithers is a project dependency.

If mcp add exits with MCP_ADD_FAILED and unknown option '--mcp', the underlying registration helper word-split the launch command and parsed --mcp as one of its own flags. Register with the agent’s own CLI instead, with a -- separator so the agent passes --mcp through to Smithers untouched:

codex mcp add smithers -- bunx smithers-orchestrator --mcp
claude mcp add smithers -- bunx smithers-orchestrator --mcp

The CLI prints these commands for you when mcp add fails. See MCP Server → If mcp add fails for the hand-written config.

The onboarding skill

The two commands above expose the CLI. The curated smithers onboarding skill goes further. It teaches the agent the mental model (Smithers as durable plan mode, the .smithers/ layout, which component to reach for) and ships the full docs bundle next to it so the agent can read the exact API on demand.

init installs the skill automatically for every detected agent. To install or re-install at any time:

bunx smithers-orchestrator skills add

Target a single agent with --agent (e.g. --agent codex, --agent cursor). See each agent’s page for the exact path where the skill lands.

Support matrix

Agent	Skill	MCP server	Notes
Claude Code	skills add	mcp add → ~/.claude.json	Also a Claude Code plugin (skill + MCP bundled)
Codex	skills add → ~/.codex/skills	mcp add / config.toml (TOML)	AGENTS.md for standing instructions
Cursor	skills add → ~/.cursor/skills	mcp add / .cursor/mcp.json	Rules in .cursor/rules/*.mdc; cursor-agent CLI
GitHub Copilot	skills add → ~/.copilot/skills	.vscode/mcp.json (editor) / repo settings (cloud agent)	Two distinct MCP schemas
Pi	skills add → ~/.pi/agent/skills	no native MCP	First-party pi-plugin with a live run inspector; see Pi integration
Hermes	skills add	mcp add → ~/.hermes/config.yaml (YAML)	Reads AGENTS.md
OpenClaw	skills add → ~/.agents/skills	mcp add → ~/.openclaw/openclaw.json	Skills via ClawHub

skills add and mcp add also reach Gemini CLI, OpenCode, Amp, Windsurf, Cline, Continue, Roo, Kilo, Goose, Augment, Trae, Junie, Crush, Kiro, Qwen Code, OpenHands. Run them once and any detected agent is wired up.

Pi, Hermes, and OpenClaw aren’t in the underlying skill/MCP framework’s built-in registry, so Smithers wires them as a supplementary step: mcp add writes the Smithers server into Hermes’s config.yaml and OpenClaw’s openclaw.json directly, and skills add copies the canonical skill set into Pi’s ~/.pi/agent/skills. Each respects --no-global, --agent, and --command, preserves existing config, and silently skips an agent that isn’t installed.

The other direction: Smithers runs the agent

Everything above is about an agent driving Smithers. Smithers also runs these agents as the workers inside a workflow. <Task agent={claude}> spawns Claude Code, <Task agent={codex}> spawns Codex, and so on, with native session hijack to take over interactively. That’s covered in CLI Agents and SDK Agents.

See also

• MCP Server: the full semantic tool reference
• Installation: the workflow pack and the onboarding skill
• Integrations: connecting Smithers to external services