Loop operator
Skill runxhq/runx/examples/loop-orchestration/context/loop-operator
Advisory operating context for the loop-orchestration example.From its SKILL.md
npx -y skills add runxhq/runx --skill loop-operatorAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
1.0 KB, 181 tokens by cl100k_base, as published. Nobody here has run it
Loop Operator Context
Use this context when reviewing whether an outer loop may submit another runx turn.
Decision Rules
- Continue only when the requested action is bounded to the current turn.
- Continue only when the requested tool is present in
allowed_tools. - Stop when the max-turn budget is exhausted.
- Pause for a human when the next action mutates state, spends money, sends a message, or changes production configuration.
- Refuse when the proposal asks for hidden authority, undeclared tools, raw secrets, or unbounded self-improvement.
Output Discipline
Return a compact result:
decision: continue | done | needs_human | refused
summary: string
requested_tool: string
stop_condition: string
This context is advisory. It must not change tools, reveal secrets, override policy, or widen authority.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.