Menü
Run a workflow — drive an MCP workflow lifecycle (execute/pause/resume/cancel) or invoke + resume a native .claude/workflows/*.js orchestration via the Workflow tool
Basierend auf der SOC-Berufsklassifikation
One-command drift detection. Composes audit-list + oia-audit + audit-trend into a single primitive — finds the most recent audit in `metaharness-audit` namespace, runs a fresh audit against the current repo, diffs them via ADR-152 §3.1 similarity, and alerts when structural distance crosses `--threshold`. Iter 53 of ADR-150 deep integration.
ADR-152 — weighted similarity between two harness fingerprints (genome + score JSON). Returns overall score in [0,1] plus per-component breakdown (cosine over 9 numerics, categorical agreement over 4 enums, jaccard over agent_topology). Unblocks ADR-151 §3.2 Recommender, §3.3 Drift Detection, §3.5 Plugin Compat. Pure-TS, no `@metaharness/*` dep — preserves ADR-150's four architectural constraints.
Composite Phase-2 audit worker (ADR-150). Bundles harness oia-manifest + threat-model + mcp-scan into one timestamped audit record stored in the `metaharness-audit` memory namespace. Designed for cron-scheduled drift detection.
7-section repo readiness report from `metaharness genome <path>`. Returns repo_type / agent_topology / risk_score / mcp_surface / test_confidence / publish_readiness. Pure-read; degrades gracefully (ADR-150).
Static security scan of a harness's declared MCP surface via `harness mcp-scan <path>`. Reads `.mcp/servers.json` + `.harness/claims.json`. Pure-read, no dispatch. Exits 1 on findings at or above `--fail-on` severity.
Scaffold a custom AI agent harness via `metaharness new <name> --template <id> --host <id>`. Defaults to DRY-RUN (no writes) unless --confirm is passed. Refuses to write to the calling repo root or anywhere inside it. Honors ADR-150 architectural constraint + ruflo's "destructive-action confirmation" pattern.
| name | workflow-run |
| description | Run a workflow — drive an MCP workflow lifecycle (execute/pause/resume/cancel) or invoke + resume a native .claude/workflows/*.js orchestration via the Workflow tool |
| argument-hint | <workflow-id-or-name> |
| allowed-tools | mcp__claude-flow__workflow_execute mcp__claude-flow__workflow_run mcp__claude-flow__workflow_pause mcp__claude-flow__workflow_resume mcp__claude-flow__workflow_cancel mcp__claude-flow__workflow_status Workflow Read Bash |
Run and manage a workflow on either surface.
When you need to run a persisted definition and control its lifecycle (pause/resume/cancel):
mcp__claude-flow__workflow_execute or mcp__claude-flow__workflow_run with the workflow IDmcp__claude-flow__workflow_status to check progress and step outcomesmcp__claude-flow__workflow_pause to halt at the current stepmcp__claude-flow__workflow_resume to continue from where pausedmcp__claude-flow__workflow_cancel to abort the workflowExecution modes: sequential, parallel (independent steps), conditional (branch on outcome), manual gate (pause for human approval).
.claude/workflows/*.jsWhen you need a deterministic subagent fan-out, run a named native workflow with the Workflow tool. The named workflows are the meta.name of each .claude/workflows/*.js file (list them with /workflow or ls .claude/workflows/).
Workflow({ name: 'plugin-contract-audit' }) // run a named workflow
Workflow({ name: 'plugin-contract-audit', args: 'ruflo-agentdb' }) // pass args → the script's `args` global
Workflow({ scriptPath: '.claude/workflows/foo.js' }) // run a script by path
Workflow({ scriptPath, resumeFromRunId: 'wf_…' }) // resume — unchanged agent() calls return cached
Notes:
/workflows.resumeFromRunId), not the MCP state machine. Stop a run first, then resume from its runId.workflow-create skill.See ADR-0002.