Skip to content
Learn Kiro.

Reference · Chapter 55 of 63

Cheat Sheet

Kiro on one page: file paths, CLI commands, slash commands, permissions, the five surfaces, and the mistakes that bite, in scannable card form.

All levels 5 min read last reviewed 2026-09-04

◎ Learning objective

Find any core Kiro fact (concept, file path, command, or workflow) in under ten seconds.

This is every Kiro fact worth memorizing, on one page, in cards you can scan in seconds. Bookmark it, and follow a card’s link when you need the full chapter behind it.

The mental model

Specswhat gets built (plan first)
Steeringwhat the agent knows
Hookswhen it acts on its own
MCP / Powerswhat it can reach
Agents / Skillswho it is / what it can do
Five surfaceswhere it all happens
Cloud sessionswhose machine runs it

Five surfaces

IDEdesktop app, VS Code-style, from kiro.dev
CLIkiro-cli in any terminal
Webapp.kiro.dev → PRs. GA since 2026-09-01, paid plans
MobileiOS app (preview): review and steer on the go
Crewopen-source, always-on, your own hardware

Kiro Crew

setupkirocrew setup
verifykirocrew doctor
runkirocrew gateway (localhost:5476)
24/7kirocrew service install
auditkirocrew security audit | verify
data~/.kiro/crew/ (KIROCREW_HOME)

Spec files

requirements.mdwhat: user stories, EARS criteria
design.mdhow: architecture, sequences
tasks.mdsteps: runs in concurrent waves
bugfix.mdbug analysis (bugfix specs)

EARS patterns

  • WHEN <event> THE SYSTEM SHALL <behavior> for normal paths
  • IF <error> THEN THE SYSTEM SHALL <handling> for error paths
  • WHILE <state> THE SYSTEM SHALL <constraint> for ongoing states
  • No IF/THEN lines = requirements not finished

Files & folders

.kiro/steering/project rules (product/tech/structure.md)
.kiro/settings/mcp.jsonworkspace MCP servers
.kiro/agents/custom agents (CLI: JSON · IDE 1.0+: Markdown)
.kiro/skills/team skills (SKILL.md)
.kiro/hooks/hooks (~/.kiro/hooks/ = global)
.kiro/specs/specs · ~/.kiro/powers/ = powers
~/.kiro/…global scope; agents: project supersedes

CLI essentials

install (macOS/Linux)curl -fsSL https://cli.kiro.dev/install | bash
install (Windows 11)irm 'https://cli.kiro.dev/install.ps1' | iex
startkiro-cli
as personakiro-cli --agent reviewer
resumekiro-cli chat --resume / --resume-picker
direct shell!command (no AI involved)
headless (CI)kiro-cli chat --no-interactive "…" + KIRO_API_KEY
trust in CI--trust-tools=read,grep · --require-mcp-startup
other editorskiro-cli acp (JetBrains, Zed)

Slash commands

/context showwhat’s loaded + token cost
/context add "glob"include files
/chat save|load <path>export / import session
/chat new [prompt]fresh session
/agent create|swapmake / switch personas
/editor /replycompose in $EDITOR
/spec runfull-screen task execution
/compactsummarize old history (CLI only, one-way)
/effortlow · medium · high · xhigh · max
/tangentbranch side-conversation
/voicedictate a prompt (on-device)
/mcp authmanage MCP auth
/upgrade-agentmigrate V2→V3 agent config
--cloud --resume-idrun / reattach a cloud session

Core workflows

  • Feature: spec → review requirements → review design → execute tasks → verify
  • Bug: bugfix spec → regression test → fix → verify
  • Refactor: steering current? → Supervised mode → small diffs → tests green
  • Chore: make it a hook, scoped narrowly

Steering rules of thumb

  • Three foundations: product.md, tech.md, structure.md
  • One domain per file, with the why
  • Modes: always · fileMatch · manual · auto
  • AGENTS.md also loads, nested, always
  • Never paste secrets into steering
  • Commit workspace steering: it’s team law

MCP config keys

  • Local: command, args, env (${VAR} expands)
  • Remote: url, headers, oauth
  • Control: disabled, disabledTools
  • autoApprove: [] default; "*" = sudo, beware
  • Debug via “Kiro - MCP Logs” channel

Modes & safety

  • Supervised: approve every hunk (learning, risky work)
  • Autopilot: end-to-end autonomy (trusted, bounded work)
  • Checkpoints: undo agent file-tool edits (IDE; CLI V3 experimental)
  • Golden rule: nothing ships unreviewed

Permissions

  • Effects: deny > ask > allow — deny always wins
  • Scopes: Kiro · admin · user · workspace · agent · session
  • User rules: ~/.kiro/settings/permissions.yaml
  • Workspace rules: ~/.kiro/workspace-roots/<hash>/permissions.yaml
  • IDE dial: Settings → Agent → kiroAgent.agentAutonomy
  • Prompt: Allow · Deny · Always allow · Always deny

.kiroignore

  • Workspace: .kiroignore (root or subdirectories)
  • Global: ~/.kiro/settings/kiroignore
  • IDE setting: kiroAgent.agentIgnoreFiles
  • Gitignore syntax, negation included; respects core.excludesfile
  • Cannot re-include inside an excluded directory
  • Support: IDE full · CLI V3 search only · Web/Mobile not yet

Top mistakes

  • Vague prompts → confident wrong code
  • Accepting diffs unread
  • autoApprove: "*" on untrusted servers
  • Hooks that trigger themselves
  • Steering files full of secrets
  • Trusting 2025 blog posts (check history)

Official links

☰ Chapter summary

  • All Kiro state lives under .kiro/ (workspace) and ~/.kiro/ (global): steering, settings, agents, skills, hooks.
  • Spec = requirements.md + design.md + tasks.md; bugfix specs use bugfix.md.
  • EARS: WHEN for normal behavior, IF/THEN for errors, WHILE for ongoing states.
  • CLI: kiro-cli to start; /context, /chat, /agent are the three command families that matter.
  • Permission effects rank deny over ask over allow, and deny wins from any scope.
  • Five surfaces: IDE, CLI, Web (GA on paid plans), iOS, and Kiro Crew on your own hardware.

All chapter summaries are collected on the revision page.

Was this chapter helpful?