# Content hub
[Home](/en/ai)
[An agent is a named role inside a setup](/en/ai/content/article/kind-agent)
- type: article
- published_at: 2026-09-04
An expanded guide to agent: specialisation, inputs, tools, limits, and a verifiable result.
[A command is a named, verifiable operation](/en/ai/content/article/kind-command)
- type: article
- published_at: 2026-09-04
An expanded guide to command: invocation interface, parameters, repeatability, and responsibility boundaries.
[A hook is an automatic action on a lifecycle event](/en/ai/content/article/kind-hook)
- type: article
- published_at: 2026-09-04
An expanded guide to hook: events, argv, determinism, side effects, and rollback.
[Standing rules are a component, not an agent role](/en/ai/content/article/kind-instruction)
- type: article
- published_at: 2026-09-04
An expanded guide to instruction: boundaries, precedence, native files, and safe distribution.
[MCP is an external tool interface, not a secret config](/en/ai/content/article/kind-mcp)
- type: article
- published_at: 2026-09-04
An expanded guide to MCP: server, client configuration, transport, permissions, and boundary checks.
[A plugin is a package that extends the harness](/en/ai/content/article/kind-plugin)
- type: article
- published_at: 2026-09-04
An expanded guide to plugin: manifest, package contents, harness projections, and installation trust.
[A setting is non-secret behavioural configuration](/en/ai/content/article/kind-setting)
- type: article
- published_at: 2026-09-04
An expanded guide to setting: config files, scope, MCP names, and the no-secrets rule.
[A skill is a workflow package, not a prompt in a folder](/en/ai/content/article/kind-skill)
- type: article
- published_at: 2026-09-04
An expanded guide to skill: triggers, procedures, progressive disclosure, and the supply-chain surface.
[Antigravity CLI](/en/ai/content/article/setup-antigravity)
- type: article
- published_at: 2026-09-04
A Gemini-based harness with skills, agents, plugins, hooks, MCP, and project resources
[Claude Code](/en/ai/content/article/setup-claude-code)
- type: article
- published_at: 2026-09-04
A terminal coding agent with CLAUDE.md, skills, agents, hooks, MCP, and versioned plugins
[Codex](/en/ai/content/article/setup-codex)
- type: article
- published_at: 2026-09-04
A coding agent with AGENTS.md, config.toml, subagents, hooks, and plugin projection
[Cursor](/en/ai/content/article/setup-cursor)
- type: article
- published_at: 2026-09-04
An IDE harness with .cursor-plugin/plugin.json, rules, skills, agents, hooks, MCP, and commands
[Grok Build](/en/ai/content/article/setup-grok-build)
- type: article
- published_at: 2026-09-04
An xAI harness with AGENTS.md, skills, plugins, hooks, MCP, and config.toml
[MiMoCode](/en/ai/content/article/setup-mimocode)
- type: article
- published_at: 2026-09-04
A system from the NDDev OpenNetwork line; ai-stp does not currently claim it as a separate supported harness.
[OpenCode](/en/ai/content/article/setup-opencode)
- type: article
- published_at: 2026-09-04
An open harness with native skills, plugins, agents, commands, MCP, and JSON configuration
- type: article
- published_at: 2026-09-04
A minimal harness with package resources, skills, extensions, prompts, and target settings
[The AI-native operating model and the project function](/en/ai/content/blog_post/agentic-operating-model)
- type: blog_post
- published_at: 2026-09-04
Why AI-native work starts with process, context, and ownership rather than model choice.
[An epitaph for old-school vibe coders](/en/ai/content/blog_post/epitaph-for-vibe-coders)
- type: blog_post
- published_at: 2026-09-04
Why prototyping without system ownership becomes an expensive theatre of misunderstanding.
[How to write Agent Skills without making an agent cosplay a junior](/en/ai/content/blog_post/skills-as-workflow)
- type: blog_post
- published_at: 2026-09-04
A practical field note on skills as workflows, not folders of Markdown.
[Vibe-coding safety: keep an agent from leaking data to production](/en/ai/content/blog_post/vibe-coding-safety)
- type: blog_post
- published_at: 2026-09-04
A practical review of secret leaks, protection layers, and safe work with AI agents.