Toolkit
Capability 07 · reviewed 2026-08-01
On this page2 sections
Commands & Invocable Workflows
Coding-AgentA worker you delegate to: brief it, and it takes steps on its own. A chatbot answers; an agent acts.An LLM that runs tools in a loop toward a goal — it acts, checks the result, decides the next step, and repeats until done.Full definition products expose two things that look alike in the PromptThe brief. Closer to writing instructions for a new contractor than to programming.The text you give the model — question, instructions, context. Its quality shapes the quality of the output.Full definition but have different contracts:
- Built-in commands control the session, model, permissions, context, or product UI.
- Custom invocable workflows package repeatable operator intent and often share machinery with skills.
Claude Code, Codex CLI, and Copilot CLI all provide interactive command surfaces. Their command names, argument conventions, availability, and persistence are product-specific. Do not build a cross-vendor process around the assumption that /name means the same thing everywhere.
Design the Workflow First
A durable custom workflow should define:
- The operator intent and accepted inputs.
- Preconditions and permission boundaries.
- A bounded sequence with explicit decision points.
- Verification that proves the requested outcome.
- A result artifact or summary that another human or agent can inspect.
Package the workflow as a skill when it needs reference files, scripts, or model-driven discovery. Keep a command as a thin, manually invoked entrypoint when direct operator timing is the value.
Safety Boundary
Invocation does not expand authority. A command named deploy should not silently infer permission to publish, spend money, or mutate external systems. Preserve the product's approval controls and require explicit confirmation at irreversible boundaries.
The deeper lenses retain Claude Code command-file examples. Claude now recommends skills for multi-step commands, while Codex and Copilot have their own command and skill precedence. Translate the workflow contract, then implement the target product's current adapter.
Documented coverage · 2026-08-01
Commands & Workflows by product
These classifications are documentation findings, not empirical runtime tests. Surface names are explicit because product-family claims are too coarse.
Claude Code
Anthropic
Claude Code provides built-in commands and invocable custom workflows; skills are now the recommended packaging model for multi-step commands.
The reviewed command reference is terminal-centered and does not establish identical IDE or hosted command availability.
Basis: documentedSources: 2
OpenAI Codex
OpenAI
Codex CLI documents an interactive slash-command surface, while repeatable custom workflows are packaged as skills.
The reviewed slash-command source is CLI-specific and does not establish identical commands on IDE, web, or cloud surfaces.
Basis: documentedSources: 4
GitHub Copilot
GitHub
Copilot CLI provides built-in slash commands plus command files as a simplified, lower-priority alternative to skills.
Basis: documentedSources: 5
The reviewed command reference is CLI-specific and does not establish identical commands elsewhere in the Copilot family.
Basis: documentedSources: 5
Source register
Commands & Workflows sources
Primary vendor documentation reviewed on the date shown. Links may change after publication.
- Extend Claude with skills (opens in a new tab)
Anthropic · official docs · accessed 2026-08-01
- Claude Code commands (opens in a new tab)
Anthropic · official docs · accessed 2026-08-01
- Build skills (opens in a new tab)
OpenAI · official docs · accessed 2026-08-01
- Codex slash commands (opens in a new tab)
OpenAI · official docs · accessed 2026-08-01
- GitHub Copilot CLI command reference (opens in a new tab)
GitHub · official docs · accessed 2026-08-01
Comparative implementation depth