dispatching-gap-analysis

Dispatching Gap Analysis

Runs /ship-review Stage 4 + Stage 4.5 as a fresh-context registered agent. The agent reads specs, delivered-code evidence, test captures, spec-review findings, and goal-verification results, then returns a structured gap list and the 10-check self-review result. The orchestrator owns all side effects: classification actions, cursor advances, stuck-counter computation, task/IDEA creation, user-facing surfacing, and read-only enforcement.

Inputs

• scope — "feature" | "sprint"
• target_ids — feature IDs, or null when scope is sprint.
• base_ref / head_ref — diff range.
• data_dir — literal <SHIPYARD_DATA> path.
• sprint_spec_paths — feature/task/reference paths under <SHIPYARD_DATA>/spec/.
• evidence_paths — Stage 1 test captures, Stage 1b spec-review findings, and Stage 3 goal-verification artifacts gathered so far.

Dispatching the Analyst

The gap-analysis methodology, classification boundaries, read-only contract, and Required Return Shape live in the registered agent agents/shipyard-gap-analyst.md — read it once if you need to know exactly what it does; do not re-inline it here.

Model tier (think). Read models.think from config.md — the invoking command skill's ! context block, or a Read of <SHIPYARD_DATA>/config.md. If the value is non-empty, pass model: <value> in the Agent call; if empty or absent, OMIT the model: field entirely so the subagent inherits the session model. Never hardcode a model literal.

Effort tier (think). Read agent_effort.think from config.md; default high. If the value is non-empty, pass effort: <value> in the Agent call; if empty or absent, OMIT effort: so the subagent inherits the runtime default.

Dispatch:

Agent(
  subagent_type: "shipyard:shipyard-gap-analyst",
  model: <models.think value, or omit>,
  effort: <agent_effort.think value, or omit>,
  prompt: "
    Scope:              {{scope}}
    Target IDs:          {{target_ids}}
    Base ref:            {{base_ref}}
    Head ref:            {{head_ref}}
    Data dir:            {{data_dir}}
    Sprint/spec paths:   {{sprint_spec_paths}}
    Evidence paths:      {{evidence_paths}}
  "
)