Skip to main content

AgentBoot CLI Reference

Reference for all implemented CLI commands. Run agentboot --help for a summary or agentboot <command> --help for command-specific help.


Global Options

FlagDescription
-c, --config <path>Path to agentboot.config.json
--verboseShow detailed output
--quietSuppress non-error output
-v, --versionPrint version

agentboot build

Compile traits into persona output files. Reads agentboot.config.json, resolves trait references, and emits self-contained output under dist/.

agentboot build
agentboot build -c path/to/config.json

agentboot validate

Run pre-build validation checks: persona existence, trait references, SKILL.md frontmatter, and secret scanning.

agentboot validate
agentboot validate --strict
FlagDescription
-s, --strictTreat warnings as errors

Exit codes: 0 = pass, 1 = errors, 2 = warnings (with --strict).


agentboot sync

Distribute compiled output from dist/ to target repositories listed in repos.json.

agentboot sync
agentboot sync --repos-file path/to/repos.json
agentboot sync --dry-run
FlagDescription
--repos-file <path>Path to repos.json (default: ./repos.json)
-d, --dry-runPreview changes without writing

agentboot dev-build

Run the full local development pipeline: clean, validate, build, dev-sync.

agentboot dev-build

This is equivalent to running clean -> validate -> build -> dev-sync in sequence. Exits on the first failure.


agentboot setup

Interactive setup wizard. Detects existing configuration and org from git remote, then scaffolds agentboot.config.json, repos.json, and core/ directories.

agentboot setup
agentboot setup --skip-detect
FlagDescription
--skip-detectSkip auto-detection of existing config and .claude/ directory

If agentboot.config.json already exists, setup exits with a message to use doctor instead.


agentboot add <type> <name>

Scaffold a new component. The name argument must be 1-64 lowercase alphanumeric characters with hyphens (e.g., my-new-persona).

agentboot add persona my-reviewer
agentboot add trait my-trait
agentboot add gotcha database-rls
agentboot add domain healthcare
agentboot add hook compliance-gate

Supported types

TypeCreates
personacore/personas/<name>/SKILL.md + persona.config.json
traitcore/traits/<name>.md
gotchacore/gotchas/<name>.md (with paths: frontmatter)
domaindomains/<name>/ directory with manifest, README, and subdirectories
hookhooks/<name>.sh (executable shell script with hook template)

agentboot doctor

Check environment and diagnose configuration issues. Validates Node.js version, git, Claude Code availability, config parsing, persona/trait existence, repos.json, and dist/ status.

agentboot doctor
agentboot doctor --format json
FlagDescription
--format <fmt>Output format: text (default), json

Exit code 1 if any issues are found.


agentboot status

Show deployment status: org info, enabled personas, traits, output formats, registered repos with sync state, and last build time.

agentboot status
agentboot status --format json
FlagDescription
--format <fmt>Output format: text (default), json

agentboot lint

Static analysis for prompt quality. Checks token budgets, vague language, hardcoded secrets, line counts, missing output format sections, and unused traits.

agentboot lint
agentboot lint --persona code-reviewer
agentboot lint --severity info
agentboot lint --format json
FlagDescription
--persona <name>Lint a specific persona only
--severity <level>Minimum severity to report: info, warn (default), error
--format <fmt>Output format: text (default), json

Exit code 1 if any errors are found.

Lint rules

RuleSeverityDescription
prompt-too-longerror/warnToken estimate exceeds budget, or line count > 500/1000
vague-instructionwarnPhrases like "be thorough", "try to", "best practice"
credential-in-prompterrorAPI keys, tokens, JWTs, hardcoded passwords
missing-output-formatinfoNo ## Output Format section in SKILL.md
trait-too-longwarnTrait exceeds 100 lines
unused-traitinfoTrait file exists but is not in traits.enabled

agentboot export

Export compiled output in a distributable format.

agentboot export
agentboot export --format plugin
agentboot export --format managed --output ./out
agentboot export --format marketplace
FlagDescription
--format <fmt>Export format: plugin (default), managed, marketplace
--output <dir>Output directory (defaults vary by format)

Export formats

FormatOutputDefault path
pluginClaude Code plugin directory.claude-plugin/
managedManaged settings for MDM deploymentmanaged-output/
marketplacemarketplace.json scaffoldcurrent directory

Requires agentboot build to have been run first (for plugin and managed formats).


agentboot publish

Publish a compiled plugin to a marketplace manifest. Reads the plugin from .claude-plugin/ or dist/plugin/, computes a SHA-256 hash, updates marketplace.json, and copies the plugin to a versioned release directory.

agentboot publish
agentboot publish --bump patch
agentboot publish --bump minor
agentboot publish --marketplace path/to/marketplace.json
agentboot publish --dry-run
FlagDescription
--marketplace <path>Path to marketplace.json (default: marketplace.json)
--bump <level>Version bump before publishing: major, minor, patch
-d, --dry-runPreview changes without writing

agentboot uninstall

Remove AgentBoot-managed files from a repository. Uses the .agentboot-manifest.json written during sync to identify managed files. Files modified after sync (hash mismatch) are skipped with a warning.

agentboot uninstall
agentboot uninstall --repo /path/to/repo
agentboot uninstall --dry-run
FlagDescription
--repo <path>Target repository path (default: current directory)
-d, --dry-runPreview what would be removed

agentboot config [key]

View configuration (read-only). Prints the full config or a specific dotted key path. Writing config values is not supported; edit agentboot.config.json directly.

agentboot config                    # Print full config
agentboot config org # Print org name
agentboot config personas.enabled # Print enabled personas list