CLI Reference

Global options

These flags apply to all subcommands:

Flag	Description
`--debug`	Enable DEBUG-level logging (default is INFO)
`-h, --help`	Print help
`-V, --version`	Print version

Fabro loads environment variables from ~/.fabro/.env.

Configuration

CLI defaults can be set in ~/.fabro/cli.toml so you don’t have to pass common flags every time:

cli.toml

[exec]
provider = "anthropic"
model = "claude-opus-4-6"
permissions = "read-write"
output_format = "text"

[llm]
model = "claude-sonnet-4-5"

CLI flags always override cli.toml values, which override hardcoded defaults.

`fabro run`

Launch a workflow from a .fabro workflow file or .toml task config.

fabro run <WORKFLOW>
fabro run run.toml
fabro run --run-branch arc/run/abc123

Argument / Flag	Description
`<WORKFLOW>`	Path to a `.fabro` workflow file or `.toml` task config. Not required when using `--run-branch`.
`--run-dir <DIR>`	Run output directory
`--dry-run`	Execute with a simulated LLM backend
`--preflight`	Validate run configuration without executing
`--auto-approve`	Auto-approve all human gates
`--resume <FILE>`	Resume from a checkpoint file
`--run-branch <BRANCH>`	Resume from a git run branch (reads checkpoint and graph from metadata branch)
`--model <MODEL>`	Override default LLM model
`--provider <PROVIDER>`	Override default LLM provider
`-v, --verbose`	Enable verbose output
`--sandbox <SANDBOX>`	Sandbox for agent tools: `local`, `docker`, `daytona`, `ssh`, or `exe`
`--label <KEY=VALUE>`	Attach a label to this run (repeatable)
`--goal <GOAL>`	Override the workflow goal (exposed as `$goal` in prompts)
`--goal-file <FILE>`	Read the goal from a file instead of inline text
`--no-retro`	Skip retro generation after the run
`--ssh`	Create SSH access to the sandbox (Daytona or exe.dev) and print the connection command
`--preserve-sandbox`	Keep the sandbox alive after the run finishes (for debugging)

--preflight conflicts with --resume, --run-branch, and --dry-run. --run-branch conflicts with --resume.

`fabro ps`

List workflow runs stored in ~/.fabro/runs.

fabro ps
fabro ps --workflow deploy --label env=prod
fabro ps --json

Flag	Description
`--before <DATE>`	Only show runs started before this date (YYYY-MM-DD prefix match)
`--workflow <NAME>`	Filter by workflow name (substring match)
`--label <KEY=VALUE>`	Filter by label (repeatable, AND semantics)
`--orphans`	Include orphan directories (no `manifest.json`)
`--json`	Output as JSON

`fabro system prune`

Delete old workflow runs. Dry-run by default — pass --yes to actually delete.

fabro system prune --before 2026-01-01
fabro system prune --before 2026-01-01 --yes
fabro system prune --orphans --yes

Flag	Description
`--before <DATE>`	Only prune runs started before this date (YYYY-MM-DD prefix match)
`--workflow <NAME>`	Filter by workflow name (substring match)
`--label <KEY=VALUE>`	Filter by label (repeatable, AND semantics)
`--orphans`	Include orphan directories (no `manifest.json`)
`--yes`	Actually delete (default is dry-run)

`fabro exec`

Run an agentic coding session. The agent operates in the current directory using file, search, and shell tools.

fabro exec "Add input validation to the signup form"
fabro exec "Fix the failing test" --provider openai --model gpt-5.2-codex
fabro exec "Refactor the auth module" --permissions full --auto-approve

Argument / Flag	Description	Default
`<PROMPT>`	Task prompt (required)	—
`--provider <PROVIDER>`	LLM provider	`anthropic`
`--model <MODEL>`	Model name	Per provider (see below)
`--permissions <LEVEL>`	Permission level: `read-only`, `read-write`, or `full`	`read-write`
`--auto-approve`	Skip interactive prompts; deny tools outside permission level	—
`--debug`	Print LLM request/response debug info to stderr	—
`--verbose`	Print full LLM request/response JSON to stderr	—
`--skills-dir <DIR>`	Directory containing skill files (overrides default discovery)	—
`--output-format <FORMAT>`	Output format: `text` (human-readable) or `json` (NDJSON event stream)	`text`
`--mode <MODE>`	`standalone` (default) or `server` — in server mode, routes through the Fabro API’s `/completions` endpoint	`standalone`
`--server-url <URL>`	Fabro API server URL (overrides `server.base_url` from `cli.toml`)	—

Permission levels control which tools are auto-approved: read-only allows read tools (read_file, grep, glob, list_dir) and subagent tools; read-write adds write tools (write_file, edit_file, apply_patch); full allows all tools including shell commands. Tools outside the permission level are either interactively prompted (if a TTY is present) or denied (with --auto-approve). See default models by provider.

`fabro llm prompt`

Send a one-shot prompt to an LLM. Accepts a prompt as an argument, via stdin, or both (stdin is prepended).

fabro llm prompt "Explain quicksort in one paragraph"
echo "Summarize this:" | fabro llm prompt
fabro llm prompt "Translate to French" -m claude-sonnet-4-5 -o temperature=0.3
fabro llm prompt -S '{"type":"object","properties":{"name":{"type":"string"}}}' "Extract the name from: John Smith"

Argument / Flag	Description
`[PROMPT]`	The prompt text (also accepts stdin)
`-m, --model <MODEL>`	Model to use
`-s, --system <SYSTEM>`	System prompt
`--no-stream`	Do not stream output
`-u, --usage`	Show token usage
`-S, --schema <SCHEMA>`	JSON schema for structured output (inline JSON string)
`-o, --option <KEY=VALUE>`	Generation options: `temperature`, `max_tokens`, `top_p`, or provider-specific keys

`fabro llm chat`

Start an interactive multi-turn chat session. In server mode, the session is backed by the Fabro server’s session endpoints.

fabro llm chat
fabro llm chat -m claude-opus-4-6 -s "You are a helpful coding assistant"
fabro llm chat --mode server

Flag	Description
`-m, --model <MODEL>`	Model to use
`-s, --system <SYSTEM>`	System prompt
`--mode <MODE>`	`standalone` (default) or `server` — in server mode, routes through the Fabro API

`fabro model list`

List available LLM models from the built-in catalog. Running fabro model with no subcommand also lists models.

fabro model list
fabro model list -p anthropic
fabro model list -q sonnet
fabro model list --mode server

Flag	Description
`-p, --provider <PROVIDER>`	Filter by provider
`-q, --query <QUERY>`	Search for models matching this string (checks ID, display name, and aliases)
`--mode <MODE>`	`standalone` (default) or `server` — in server mode, fetches the catalog from the Fabro API

`fabro model test`

Test model availability by sending a simple prompt to each model and reporting the result.

fabro model test
fabro model test -p anthropic
fabro model test -m claude-sonnet-4-5

Flag	Description
`-p, --provider <PROVIDER>`	Filter by provider
`-m, --model <MODEL>`	Test a specific model

`fabro serve`

Start the HTTP API server that exposes the REST API for launching and managing workflow runs.

fabro serve
fabro serve --port 8080 --host 0.0.0.0
fabro serve --sandbox daytona --max-concurrent-runs 4

Flag	Description	Default
`--port <PORT>`	Port to listen on	`3000`
`--host <HOST>`	Host address to bind to	`127.0.0.1`
`--model <MODEL>`	Override default LLM model	—
`--provider <PROVIDER>`	Override default LLM provider	—
`--dry-run`	Execute with simulated LLM backend	—
`--sandbox <SANDBOX>`	Sandbox for agent tools: `local`, `docker`, `daytona`, `ssh`, or `exe`	—
`--max-concurrent-runs <N>`	Maximum number of concurrent run executions	—
`--config <PATH>`	Path to server config file	`~/.fabro/server.toml`

Demo mode is per-request: send the X-Fabro-Demo: 1 header to get static demo data with auth disabled. If no LLM provider API keys are configured, the server automatically falls back to dry-run mode.

`fabro cp`

Copy files between a run’s sandbox and the local filesystem. The run must have a persisted sandbox record (Daytona, exe.dev, or a preserved local/Docker sandbox).

fabro cp <run-id>:/path/in/sandbox ./local-dir     # download
fabro cp ./local-file <run-id>:/path/in/sandbox     # upload
fabro cp -r <run-id>:/output ./results              # recursive download

Argument / Flag	Description
`<SRC>`	Source: `<run-id>:<path>` for sandbox, or a local path
`<DST>`	Destination: `<run-id>:<path>` for sandbox, or a local path
`-r, --recursive`	Recurse into directories

Run IDs support prefix matching — you can use the first few characters instead of the full ID.

`fabro pr`

Manage GitHub pull requests created by workflow runs. Requires a GitHub App to be configured.

`fabro pr create`

Create a GitHub pull request from a completed workflow run. Uses the run’s persisted manifest, conclusion, and diff.

fabro pr create <run-id>
fabro pr create <run-id> --model claude-opus-4-6

Argument / Flag	Description
`<RUN_ID>`	Run ID or prefix (required)
`--model <MODEL>`	LLM model for generating the PR description

The run must have completed successfully (or with partial success) and have a final.patch with changes.

`fabro pr list`

List all pull requests created by workflow runs. Shows PR number, title, status, and the associated run ID.

fabro pr list
fabro pr list --all

Flag	Description
`--all`	Include closed and merged PRs (default: open only)

`fabro pr view`

Show details of a pull request from a specific run.

fabro pr view <run-id>

Argument	Description
`<RUN_ID>`	Run ID or prefix (required)

`fabro pr merge`

Merge a pull request from a specific run.

fabro pr merge <run-id>
fabro pr merge <run-id> --method rebase

Argument / Flag	Description
`<RUN_ID>`	Run ID or prefix (required)
`--method <METHOD>`	Merge method: `squash` (default), `merge`, or `rebase`

`fabro pr close`

Close a pull request from a specific run without merging.

fabro pr close <run-id>

Argument	Description
`<RUN_ID>`	Run ID or prefix (required)

`fabro system df`

Show disk usage of Fabro’s data directory, including run logs, worktrees, server logs, and databases.

fabro system df
fabro system df -v

Flag	Description
`-v, --verbose`	Show per-run breakdown

`fabro graph`

Render a workflow DOT graph as SVG or PNG. Requires Graphviz (dot) to be installed.

fabro graph workflow.fabro
fabro graph workflow.fabro --format png -o diagram.png
fabro graph run.toml --format svg

Argument / Flag	Description
`<WORKFLOW>`	Path to a `.fabro` workflow file or `.toml` run config (required)
`--format <FORMAT>`	Output format: `svg` (default) or `png`
`-o, --output <FILE>`	Output file path. Defaults to stdout.

`fabro skill install`

Install the built-in fabro-create-workflow skill for AI assistants (Claude Code, Codex). The skill teaches AI assistants Fabro’s DOT syntax, node types, and run configuration format.

# Install into the current project (.claude/skills/ or .agents/skills/)
fabro skill install --for project --dir claude

# Install for all projects (user-level, ~/.claude/skills/)
fabro skill install --for user --dir claude

Flag	Description
`--for <SCOPE>`	`user` (default) — installs to `~/<dir>/skills/`. `project` — installs to `./<dir>/skills/`.
`--dir <DIR>`	Directory convention: `claude` (`.claude/skills/`) or `agents` (`.agents/skills/`). Required.
`--force`	Overwrite an existing installation without prompting.

`fabro validate`

Validate a workflow file without executing it. Reports errors and warnings. Accepts both .fabro workflow files and .toml run configs.

fabro validate workflow.fabro
fabro validate run.toml

Argument	Description
`<WORKFLOW>`	Path to a `.fabro` workflow file or `.toml` run config (required)

`fabro parse`

Parse a DOT file and print its AST as JSON. Useful for debugging workflow definitions.

fabro parse workflow.fabro

Argument	Description
`<WORKFLOW>`	Path to the `.fabro` workflow file (required)

`fabro init`

Initialize a new Fabro project in the current git repository. Creates an fabro.toml project config and a sample hello workflow.

fabro init

The command must be run inside a git repository. It creates:

fabro.toml — project configuration with comments and a link to docs
fabro/workflows/hello/workflow.fabro — a simple greeting workflow
fabro/workflows/hello/workflow.toml — run config for the hello workflow

`fabro diff`

Show the diff from a workflow run. Displays the final.patch for completed runs, or connects to the sandbox for a live diff from in-progress runs.

fabro diff <run-id>
fabro diff <run-id> --node work
fabro diff <run-id> --stat

Argument / Flag	Description
`<RUN>`	Run ID or prefix (required)
`--node <NODE>`	Show diff for a specific node instead of the full run
`--stat`	Show diffstat instead of full patch (live diffs only)
`--shortstat`	Show only files-changed/insertions/deletions summary (live diffs only)

Output is colorized when writing to a terminal.

`fabro ssh`

SSH into a Daytona sandbox from a completed or in-progress run. Creates temporary SSH credentials and connects directly, or prints the command with --print.

fabro ssh <run-id>
fabro ssh <run-id> --print
fabro ssh <run-id> --ttl 120

Argument / Flag	Description
`<RUN>`	Run ID or prefix (required)
`--ttl <MINUTES>`	SSH credential expiry in minutes (default: 60)
`--print`	Print the SSH command instead of connecting

See SSH Access for more details on SSH workflows.

`fabro preview`

Generate a preview URL for a port exposed by a Daytona sandbox. Useful for accessing web servers, dev tools, or APIs running inside the sandbox.

fabro preview <run-id> <port>
fabro preview <run-id> 3000 --signed
fabro preview <run-id> 3000 --open

Argument / Flag	Description
`<RUN>`	Run ID or prefix (required)
`<PORT>`	Port number to preview (required)
`--signed`	Generate a signed URL (self-contained, no headers needed)
`--ttl <SECONDS>`	Signed URL expiry in seconds (default: 3600, requires `--signed`)
`--open`	Open the URL in a browser (implies `--signed`)

Without --signed, the command prints the URL, token, and a curl example. See Preview for more details.

`fabro doctor`

Check environment and integration health. Verifies system dependencies, API keys, and optional services. Probes live services (LLM providers, sandbox, GitHub App) by default.

fabro doctor
fabro doctor -v
fabro doctor --dry-run

Flag	Description
`-v, --verbose`	Show detailed information for each check
`--dry-run`	Skip live service probes (LLM, sandbox, API, web, Brave Search)

`fabro install`

Interactive setup wizard that walks you through configuring API keys and validating your environment. Runs fabro doctor with live probes after setup to validate the configuration.

fabro install

Getting Started

Core Concepts

Defining Workflows

Executing Workflows

Human Tools

Agents

Integrations

Reference

CLI Reference

Global options

Configuration

`fabro run`

`fabro ps`

`fabro system prune`

`fabro exec`

`fabro llm prompt`

`fabro llm chat`

`fabro model list`

`fabro model test`

`fabro serve`

`fabro cp`

`fabro pr`

`fabro pr create`

`fabro pr list`

`fabro pr view`

`fabro pr merge`

`fabro pr close`

`fabro system df`

`fabro graph`

`fabro skill install`

`fabro validate`

`fabro parse`

`fabro init`

`fabro diff`

`fabro ssh`

`fabro preview`

`fabro doctor`

`fabro install`

Getting Started

Core Concepts

Defining Workflows

Executing Workflows

Human Tools

Agents

Integrations

Reference

​Global options

​Configuration

​fabro run

​fabro ps

​fabro system prune

​fabro exec

​fabro llm prompt

​fabro llm chat

​fabro model list

​fabro model test

​fabro serve

​fabro cp

​fabro pr

​fabro pr create

​fabro pr list

​fabro pr view

​fabro pr merge

​fabro pr close

​fabro system df

​fabro graph

​fabro skill install

​fabro validate

​fabro parse

​fabro init

​fabro diff

​fabro ssh

​fabro preview

​fabro doctor

​fabro install

Global options

Configuration

`fabro run`

`fabro ps`

`fabro system prune`

`fabro exec`

`fabro llm prompt`

`fabro llm chat`

`fabro model list`

`fabro model test`

`fabro serve`

`fabro cp`

`fabro pr`

`fabro pr create`

`fabro pr list`

`fabro pr view`

`fabro pr merge`

`fabro pr close`

`fabro system df`

`fabro graph`

`fabro skill install`

`fabro validate`

`fabro parse`

`fabro init`

`fabro diff`

`fabro ssh`

`fabro preview`

`fabro doctor`

`fabro install`