Menu
Execute a bundled or project-local flowai-workflow DAG. Use to launch a workflow run from inside the host IDE.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Supervisor for one flowai-workflow run (Codex). Starts or resumes a single workflow, diagnoses failures from run artifacts, patches root causes, resumes the same run. Run inside an isolated Codex worker subagent spawned by the `supervise`/`orchestrate` skill.
Copy a bundled flowai-workflow into the user's project so they can adapt and run it locally. Use when the user wants to start using flowai-workflow in a new repo.
Run the flowai-workflow orchestration policy loop. Delegates policy execution to the workflow orchestrator agent, which selects workflows from ORCHESTRATION.md and supervisor summaries.
Live flowai-workflow run supervisor. Use only for requests to run, monitor, continue, or resume a current workflow now. Exclude last-night, finished, post-mortem, root-cause-report, and conceptual questions.
Long-cycle flowai-workflow orchestrator (Codex). Reads project orchestration policy, selects the next workflow, and returns a structured supervisor delegation request. Run inside an isolated Codex worker subagent spawned by the `orchestrate` skill.
Scaffold or adapt flowai-workflow DAGs in a project. Use for adding flowai-workflow, adapting an existing .flowai-workflow/<name>, validating workflow.yaml, or wiring agent prompts/scripts.
| name | run |
| description | Execute a bundled or project-local flowai-workflow DAG. Use to launch a workflow run from inside the host IDE. |
| argument-hint | workflow name or path (e.g. github-inbox or .flowai-workflow/<name>) |
| effort | low |
Execute a flowai-workflow DAG via the flowai-workflow engine binary
(plugin precondition — FR-E78). The binary itself bundles the canonical
workflows; the operator may also adapt a project-local copy under
<project-root>/.flowai-workflow/<name>/.
Before launching, verify the engine is on PATH:
command -v flowai-workflow >/dev/null 2>&1 || { echo "Error: flowai-workflow is required — see https://github.com/korchasa/flowai-workflow#install" >&2; exit 127; }
If the binary is missing, stop and surface the install link. Do not silently fall back to a different runtime.
The first positional argument names the workflow. Resolve it in this order:
workflow.yaml,
use it as-is.<project-root>/.flowai-workflow/, use the project-local copy.flowai-workflow init --list).flowai-workflow run "<resolved-workflow-path>" [extra args]
Forward any additional CLI flags the user provides (e.g. --prompt,
--dry-run, --cycles). Stream output back to the user in normal
verbosity unless they asked for -v / -q.
--prompt "<text>" — extra context for the PM agent--resume <run-id> — resume a previous run--dry-run — print the execution plan without running-v / -s / -q — verbose / semi-verbose / quiet--cycles <N> — repeat the run N times sequentiallyscaffold to adapt the config.<workflow>/runs/<run-id>/ and the per-run worktree; if the
workflow lives in a read-only location, instruct the user to first
/flowai-workflow:init into their project so runs can write into
the project-local copy.