@workflow-manager/runner/dist/manPage.d.ts

CLI runner for in-memory and markdown workflow orchestration using ATEP-like envelopes

export declare const MAN_PAGE_SOURCE = ".TH WFM 1 \"April 2026\" \"@workflow-manager/runner\" \"User Commands\"\n.SH NAME\nwfm \\- run markdown or json workflows from the CLI\n.SH SYNOPSIS\n.B wfm\n.I command\n[options]\n.SH DESCRIPTION\nwfm parses a workflow definition file, validates it, and executes\nit with deterministic in-memory orchestration.\n\nWorkflow files can be Markdown with YAML frontmatter or JSON.\n.SH COMMANDS\n.TP\n.B doctor [workflow.md|workflow.json] [--json]\nInspect host adapter setup, LLM access keys, and current adapter implementation status. When a workflow path is provided, also validate schema and runtime requirements without executing steps.\n.TP\n.B skill list\nList the agent skills bundled with the npm package.\n.TP\n.B skill install [name ...] [--agent claude|opencode] [--global] [--dir path] [--all] [--force]\nInstall bundled agent skills into an agent skill directory. Defaults to the workflow-manager-cli skill and the project-level Claude Code directory (./.claude/skills). Existing skills are not overwritten unless --force is passed.\n.TP\n.B scaffold [path] [--format markdown|json] [--template default|agent-validated]\nCreate a starter workflow file. Format defaults to markdown unless the output\npath ends in .json. Template defaults to default (the general multi-step example);\nagent-validated scaffolds a compact pipeline demonstrating first-class agent\nvalidation (validation.mode: agent with a validator agent and criteria).\n.TP\n.B validate <workflow.md|workflow.json>\nValidate workflow structure and report schema errors.\n.TP\n.B judge <workflow.md|workflow.json> [--json] [--adapter key] [--model model]\nLLM-judge a workflow for model right-sizing and complexity before running it. Validates first, then never spends tokens on an invalid workflow. --adapter selects the executing adapter (default pi-agent; mock for a free dry-run), --model selects the model used for judging, --json prints the raw verdict.\n.TP\n.B run <workflow.md|workflow.json> [--input input.json] [--objective text] [--confirm list] [--auto-confirm-all] [--port number] [--session-file path] [--verbose] [--json] [--ui]\nRun the workflow with live CLI progress and optional JSON output.\n.TP\n.B approve [--url value] [--token value] [--session-file path] [--run-id value] [--step value] [--actor value] [--note text]\nApprove the current waiting runner step through the local attach API.\n.TP\n.B resume [--url value] [--token value] [--session-file path] [--run-id value] [--step value] [--actor value] [--note text]\nAlias for approve, intended for external resume flows.\n.TP\n.B cancel [--url value] [--token value] [--session-file path] [--run-id value] [--step value] [--actor value] [--note text]\nCancel the current waiting runner step through the local attach API.\n.TP\n.B status [--url value] [--token value] [--session-file path] [--run-id value] [--step key]\nPrint the current run snapshot (or one step detail with --step) as JSON on stdout.\n.TP\n.B logs [--url value] [--token value] [--session-file path] [--run-id value] [--step key] [--limit number] [--cursor value]\nPrint buffered agent stdout/stderr chunks as JSON on stdout.\n.TP\n.B events [--url value] [--token value] [--session-file path] [--run-id value] [--since sequence] [--include-logs]\nPrint run events as JSON on stdout in a single poll (no streaming). Log events are excluded unless --include-logs is passed.\n.TP\n.B auth <login|whoami|logout> [--token value]\nManage remote registry authentication for CLI publish and pull flows.\n.TP\n.B publish <workflow.md|workflow.json> [--slug slug] [--title text] [--description text] [--visibility public|private] [--version label] [--tag a,b] [--draft]\nPublish a validated local workflow to the remote registry.\n.TP\n.B pull <owner/slug> [--version label] [--output path]\nDownload a remote workflow and write it to a local file.\n.TP\n.B search [query]\nSearch public workflows from the remote registry.\n.TP\n.B remote info <owner/slug>\nShow metadata and source information for a remote workflow.\n.TP\n.B man\nOpen this man page.\n.TP\n.B --version, -v, version\nPrint the installed wfm version and exit.\n.SH RUN OPTIONS\n.TP\n.B --input <path>\nJSON file merged into global workflow input state.\n.TP\n.B --objective <text>\nOverride the default run objective.\n.TP\n.B --confirm <stepA,stepB:human,...>\nProvide explicit confirmations for steps that require validation.\n.TP\n.B --auto-confirm-all\nBypass confirmation gating for all steps.\n.TP\n.B --port <number>\nBind the local attach API to a specific port. If omitted, the OS assigns a free port on 127.0.0.1.\n.TP\n.B --session-file <path>\nWrite attach connection details (base URL, bearer token, run id, pid, timestamps) to a JSON file with mode 0600 when the run starts, and rewrite it with endedAt and the final status when the run finishes. Attach commands (approve, resume, cancel, status, logs, events) accept the same flag to read those details back.\n.TP\n.B --verbose\nStream per-step agent output and execution updates to stderr while the workflow runs.\n.TP\n.B --json\nPrint the final run result as JSON on stdout while keeping live progress on stderr.\n.TP\n.B --ui\nFull-screen terminal UI (requires a TTY; falls back to standard output).\n.TP\nHuman approval steps in an interactive terminal show an inline review prompt so they can be approved or cancelled without a separate HTTP client.\n.TP\n.B --url <value>\nRunner attach API base URL for approve, resume, cancel, status, logs, or events commands.\n.TP\n.B --token <value>\nRunner attach API bearer token for approve, resume, cancel, status, logs, or events commands.\n.TP\n.B --run-id <value>\nRunner id to control. If omitted, the CLI reads it from /session.\n.TP\n.B --step <value>\nOptional step key when controlling a specific waiting step, or when scoping status and logs output.\n.TP\n.B --limit <number>\nMaximum number of log chunks returned by the logs command. Defaults to 200.\n.TP\n.B --cursor <value>\nPagination cursor for the logs command, taken from a previous nextCursor value.\n.TP\n.B --since <sequence>\nOnly return events with a sequence greater than this value in the events command.\n.TP\n.B --include-logs\nInclude agent.stdout and agent.stderr events in the events command output.\n.TP\n.B --actor <value>\nActor name recorded in approval audit events.\n.TP\n.B --note <text>\nOptional approval or cancellation note recorded in the event payload.\n.SH EXAMPLES\n.TP\nValidate markdown workflow:\n.B wfm validate ./example-workflow.md\n.TP\nValidate json workflow:\n.B wfm validate ./example-workflow.json\n.TP\nJudge a workflow before running it:\n.B wfm judge ./example-workflow.json\n.TP\nScaffold json workflow file:\n.B wfm scaffold ./new-workflow.json --format json\n.TP\nScaffold an agent-validated pipeline example:\n.B wfm scaffold ./agent-validated.md --template agent-validated\n.TP\nAuthenticate with a CLI token:\n.B wfm auth login --token wm_exampletoken\n.TP\nPublish a workflow:\n.B wfm publish ./example-workflow.json --visibility public --tag example,automation\n.TP\nPull a remote workflow:\n.B wfm pull alice/remote-bunny --output ./remote-bunny.json\n.TP\nSearch the remote registry:\n.B wfm search bunny\n.TP\nRun with explicit confirmations:\n.B wfm run ./example-workflow.json --confirm discover:human,qa_gate:human\n.TP\nRun with a session file for attach clients:\n.B wfm run ./example-workflow.json --session-file ./run-session.json\n.TP\nObserve and control the run through the session file:\n.B wfm status --session-file ./run-session.json && wfm approve --session-file ./run-session.json --step qa_gate\n.TP\nInspect host setup:\n.B wfm doctor\n.TP\nCheck a workflow before running it:\n.B wfm doctor ./example-workflow.json\n.TP\nInstall the bundled CLI skill for Claude Code:\n.B wfm skill install\n.TP\nInstall every bundled skill globally:\n.B wfm skill install --all --global\n.SH FILES\n.TP\n.B man/wfm.1\nThe manual page source shipped with this repository.\n.SH EXIT STATUS\n.TP\n.B 0\nSuccessful command execution.\n.TP\n.B 1\nValidation or runtime error.\n.TP\n.B 2\nRun completed in non-success terminal status.\n";