ClawHub

Agent Orchestrator Template

v0.1.1

A skill for main agents that need bounded delegation, safe parallel dispatch, and independent acceptance across multiple specialists.

⭐ 0· 124·0 current·0 all-time
byBiu@cjke84
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name and description match the SKILL.md and referenced templates: this is a routing/orchestration policy for a main agent. There are no unrelated environment variables, binaries, or install steps requested that would be disproportionate to an orchestrator template.
ℹ
Instruction Scope
The instructions are focused on classification, task-contract creation, dispatch, verification, and recovery. They reference local scripts and resume/state files (e.g., scripts/verify-openclaw-local.sh, scripts/resume-orchestration.py, scripts/state-store.py) and expect a local OpenClaw profile with five allowed sub-agents; those scripts and runtime artifacts are not included in this bundle. That is not malicious, but you should verify these external scripts and the runtime environment before using the templates in automation.
✓
Install Mechanism
No install spec and no code files — instruction-only — so nothing is written to disk or fetched during install by the skill itself. This is low-risk from an install perspective.
✓
Credentials
The skill declares no required environment variables, no credentials, and no config paths. The guidance operates purely on routing/contract semantics and local agent ids, so the absence of secrets or unrelated credentials is proportionate.
✓
Persistence & Privilege
always is false and default autonomous invocation is allowed (platform default). The skill does not request persistent system-wide privileges or attempt to modify other skills' configs. It references local runtime resume artifacts but does not require being force-enabled.
Assessment
This skill is an instruction-only orchestration template and appears internally consistent with its purpose. Before enabling it in an automated agent: 1) Confirm your local OpenClaw runtime actually exposes the allowed sub-agent ids (codex, invest, content, knowledge, community) and enforces the stated concurrency limits; 2) Inspect or obtain the external scripts and tooling it references (scripts/verify-openclaw-local.sh, scripts/resume-orchestration.py, scripts/state-store.py and any resume/state files) from a trusted source — they are not bundled here; 3) If you do not want autonomous dispatching, apply runtime controls or policy limits on model-invoked skill calls; 4) If you will rely on the example GitHub repo (cjke84/agent-orchestrator-template), review that repository for additional files or behavior not present in this bundle. The skill is coherent and low-risk, but validate the referenced runtime artifacts and test the orchestration rules in a controlled environment before using in production.

Like a lobster shell, security has layers — review code before you run it.

latestvk979v1g4v5n6tjfda7qd52q1f183mwsd

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments