Goal Analysis — Autonomous Agents Agentic Workflow

schema_version: 1
id: agent_pm_goal_analysis
title: "Goal Analysis"
description: "Read-only: analyze an epic's scope, dependencies, risks and open decisions, then post one decision-oriented comment — no issues, no code, no dispatch"
overview: |
  A read-only analysis pass for an epic (the analyzed ticket is usually the epic itself). The PM agent
  reads the epic and its ENTIRE comment thread — any prior context, analysis, or answers already posted
  — grounds itself in the relevant skill packs and the codebase, then posts a single comment: scope,
  dependency waves, risks, sizing, a decision overview (each decision with options and a
  recommendation), and the open questions to resolve before breakdown.

  Prior context enriches the analysis but is not required; the pass proceeds with whatever is in the
  thread. It is phase-aware and idempotent — a fresh epic gets a full analysis, an already-analyzed
  epic gets a delta. No issues are created and no work is dispatched. The verdict reports whether the
  epic is ready to break down or has open decisions to resolve first. Use it as the analysis step of
  the goal-shaping flow, or standalone on any epic.

category:
  level: pipeline
  domain: engineering

metadata:
  agent: true
  role: pm

params:
  ticket_url:
    type: string
    description: "Jira epic URL (the ticket to analyze; usually the epic itself)"
  hint:
    type: string
    default: ""
    description: "Optional extra instructions for the agent"
  entry_path:
    type: string
    default: "~/workspace"
    description: "Working directory for the agent"

steps:
  - type: terminal.open
    title: "Agent: PM Goal Analysis"
    cwd: "{{entry_path}}"
  - type: terminal.run
    cmd: |
      source ~/.agent-env && claude --dangerously-skip-permissions "$(cat <<'SB_PROMPT'
      read the ticket with attachments and ALL comments - {{ticket_url}}; it is usually the epic itself. also read its child issues, if any, and any linked or blocking epics. if it fails, stop and report the error.
      this is a READ-ONLY analysis pass.
      learn the area first - ground yourself in the relevant skill packs and the codebase (modules, dependencies, data model) before scoping.
      detect phase and act idempotently:
        - NEW (no prior analysis): produce a full analysis.
        - EXISTING (analysis already posted, or the epic already has children): produce a DELTA - surface only what is new (scope drift, a fresh blocker, missing work).
      analyze the epic and produce:
        - SCOPE: what is in, what is out (one line each)
        - DEPENDENCIES: intra-epic and cross-epic blockers, grouped into parallel waves (wave 1 = nothing blocks it)
        - RISKS: edge cases, what could break, environments and data touched
        - SIZING: rough size per area (S / M / L)
        - DECISIONS: each open decision with its options and your recommendation
        - QUESTIONS: the open questions to answer before breakdown
      {{hint}}
      post ONE comment to the ticket with the sections above, as clear prose; keep DECISIONS and QUESTIONS as their own labelled lists.
      end with one line - "VERDICT:" followed by exactly one of READY_TO_PLAN (analysis complete, nothing blocks breakdown) / NEEDS_DECISIONS (open decisions or questions must be answered first) / NO_CHANGE (re-analysis found nothing material to add) - and use these uppercase tokens nowhere else in the comment.
      SB_PROMPT
      )"