Menü
Kiro CLI agent JSON schema, valid fields, tool mappings, hooks, and common mistakes. Use when creating or modifying crew YAML or agent configurations.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | kiro-cli-schema |
| description | Kiro CLI agent JSON schema, valid fields, tool mappings, hooks, and common mistakes. Use when creating or modifying crew YAML or agent configurations. |
{
"name": "string (required)",
"description": "string",
"prompt": "string | file:// URI",
"tools": ["tool-name"],
"allowedTools": ["tool-name"],
"toolsSettings": { "canonical_name": {} },
"resources": ["file://path", "skill://path"],
"hooks": { "hookType": [{ "command": "...", "matcher": "..." }] },
"mcpServers": { "serverName": { "command": "...", "args": [], "env": {} } },
"keyboardShortcut": "modifier+key",
"welcomeMessage": "string"
}
| Canonical (use in toolsSettings) | Aliases (valid in tools/allowedTools) |
|---|---|
fs_read | read, fsRead |
fs_write | write, fsWrite |
execute_bash | shell, execute_cmd |
crew | subagent, agent_crew, use_subagent |
todo_list | task, todo |
Rule: toolsSettings keys MUST use canonical names.
fs_write:
allowedPaths: ["src/**"]
deniedPaths: ["node_modules/**"]
execute_bash:
allowedCommands: ["git *", "npm test"]
deniedCommands: ["rm -rf *"]
autoAllowReadonly: true
crew:
availableAgents: ["researcher", "builder"] # supports globs
trustedAgents: ["researcher", "builder"] # auto-approved
| Hook | When | matcher required? | Notes |
|---|---|---|---|
agentSpawn | Session start | No | Output injected into context |
stop | After every response | No | Keep fast (<2s) |
postToolUse | After specific tool | Yes | Good for auto-lint |
preToolUse | Before specific tool | Yes | Exit 2 = block call |
Environment: $KIRO_FILE_PATH available in fs_write matcher hooks.
resources:
- file://.kiro/steering/**/*.md # always loaded (glob)
- skill://.kiro/skills/my-skill.md # loaded on keyword trigger
workflow: crew-name
architypes: # NOTE: spelling is "architypes" (not "archetypes")
- type: orchestrator # orchestrator | worker
tools: [read, subagent]
prompt: |
Archetype-level prompt
agents:
- name: agent-name
description: ""
keyboardShortcut: "ctrl+shift+x"
welcomeMessage: ""
prompt: |
Agent-level prompt (appended to archetype prompt)
autoApprove is not a valid field — use allowedTools for auto-approvedeniedCommands: []) — omit entirelytoolsSettings with alias keys (shell: instead of execute_bash:) — silently ignoredcrews/ directory — only agentSpawn deploys to generated agentsWrite Architecture Decision Records when making significant technical choices. Use when selecting tools, patterns, frameworks, or making structural changes that future developers need to understand.
Write AGENTS.md files that serve as operating contracts for AI agents. Use when creating or updating AGENTS.md for a project. Trigger terms: AGENTS.md, agent instructions, agent contract, agent configuration, coding agent setup.
Quality rules for changelog entries. Use when validating, writing, or reviewing changelog content to ensure user-facing value communication.
Task completion sequence including verification, git, signaling, and handoff. Use when finishing a task or reporting status.
Architecture diagrams for documentation. Covers ASCII, Mermaid, C4, and D2. Applies C4 methodology by default. Trigger terms: diagram, flowchart, architecture diagram, sequence diagram, C4, mermaid, ascii diagram.
Classify documentation by audience and content type. Use when planning, auditing, or placing project documentation.