korchasa/orchestrate
claude-plugin/plugins/flowai-workflow/skills/orchestrate/SKILL.md
Run the flowai-workflow orchestration policy loop. Delegates policy execution to the workflow orchestrator agent, which selects workflows from ORCHESTRATION.md and supervisor summaries.
data-ai
Updated May 25, 2026
$ install --global
skillsauthnpx skillsauth add korchasa/flowai-workflow orchestrateInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 25, 2026, 4:24 AM184.4s1 file scanned
SKILL.md
- name:
- orchestrate
- description:
- Run the flowai-workflow orchestration policy loop. Delegates policy execution to the workflow orchestrator agent, which selects workflows from ORCHESTRATION.md and supervisor summaries.
- argument-hint:
- optional .flowai-workflow path or loop limit
- effort:
- high
Workflow Orchestration Entry
Start or continue a project-local flowai-workflow orchestration loop. This is
the public entry point and dispatch bridge. Policy decisions belong to
orchestrator; run recovery belongs to
supervisor.
Dispatch Loop
- Launch
orchestratorwith the host's real subagent mechanism:- Claude Code: use the
Agent/Tasktool withsubagent_type=orchestrator; - OpenCode: use the
@orchestrator <task prompt>mention syntax.
- Claude Code: use the
- Ask it to read policy/history, append its decision, and return either:
STOP: <reason>; or- a
SUPERVISOR_DELEGATIONblock with workflow path, optional run id, reason, and requested short-result fields.
- If it returns
SUPERVISOR_DELEGATION, launchsupervisorfrom the parent context using the real subagent mechanism:- Claude Code:
Agent/Taskwithsubagent_type=supervisor; - OpenCode:
@supervisor <task prompt>.
- Claude Code:
- Pass the supervisor only one workflow/run and ask for a short result:
workflow,run_id,status,fixes,repeat,blocker. - Feed that short result into the next orchestrator call if the policy loop should continue. Stop when the policy stop condition, supervisor blocker, or user loop limit is reached.
Pass the orchestrator:
- the user's request;
- repository root;
- optional loop limit, if the user gave one;
- prior supervisor summary, when continuing after a supervised run;
- instruction to return concise progress plus a structured delegation block.
If the current IDE has no native subagent dispatch, say that context-isolated
orchestration is unavailable in this IDE and stop. Do not inline the loop in the
parent context. Do not simulate delegation with bash, echo, heredocs, or
placeholder text.
Parent Boundaries
The parent session may identify that .flowai-workflow/ exists, but must not:
- choose workflows by policy;
- read
.flowai-workflow/ORCHESTRATION.mddeeply; - read workflow
runs/,state.json,journal.jsonl,logs/, or node artifacts; - patch workflow files;
- run
flowai-workflowdirectly for a selected workflow.
Those actions belong to the orchestrator subagent and, for a single run, the supervisor subagent. The parent only dispatches between them because some hosts do not allow nested subagent calls.
Expected Subagent Result
Ask the orchestrator to report:
- decisions appended to
.flowai-workflow/orchestration.jsonl; - selected workflows, supervisor delegation requests, and supervisor run ids;
- final stop condition or next pending action;
- blockers requiring a real user decision.
Related Skills
korchasa/supervisor
development
VerifiedTrustedCommunity
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.
SKILL.mdUpdated Jun 4, 2026
korchasa/orchestrator
development
VerifiedTrustedCommunity
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.
SKILL.mdUpdated Jun 4, 2026
korchasa/supervise
data-ai
VerifiedTrustedCommunity
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.
SKILL.mdUpdated May 31, 2026
korchasa/scaffold
data-ai
VerifiedTrustedCommunity
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.
SKILL.mdUpdated May 31, 2026