caller-options

# /caller-options **Caller Options (COP)** makes a skill's hidden choices visible. When a participating skill runs, COP detects whether the invocation has *material optionality* along two dimensions, evaluates the live options, and surfaces them to the caller — instead of the skill silently picking. The caller (a human, or another agent) decides. - **Venue** — *who* executes: `inline` (the active agent), `delegated` (one primed sub-agent, while the active agent orchestrates — the "agentic counterpart"), or `fan-out` (N parallel sub-agents). - **Mode** — *which path* of the skill, when the skill already has more than one. COP is invoked two ways: **automatically**, when a skill carrying the COP opt-in block is triggered; or **directly**, as `/caller-options <task or skill>` for an ad-hoc routing decision. ## The protocol — five steps COP always runs in the **active agent** — the venue decision cannot itself be delegated. 1. **Triage.** Read the triggered skill's `caller-options` declaration and the task. If exactly one venue *and* one mode clearly dominate, **skip straight to execute** — do not prompt the caller. This anti-nag gate resolves most invocations. 2. **Enumerate.** List the viable `mode × venue` combinations. Drop `delegated`/`fan-out` if the skill is on the never-delegate list, is self-orchestrating (spawns its own sub-agents — wrapping it would nest to depth 2), or if a resolved-invocation marker is present (depth guard). 3. **Assess.** Evaluate the survivor...