A

Autonomous Agents Agentic Workflow

Investigate + Plan — Autonomous Agents Agentic Workflow

Read-only: investigate the ticket and draft a concrete work plan — no code changes, no PR

Available free v1.4.1 Browser
$ sidebutton install agents
Download ZIP
se

A read-only planning pass for any ticket — feature, refactor, or task — that produces an implementation plan before any code is written. The software engineer agent reads the ticket and the relevant code, configs, schemas, and any linked PRs, designs, or mockups, then posts a concrete work plan: the goal and acceptance criteria, the approach and key files to change, an ordered step checklist, risks and edge cases, a test strategy, and a complexity estimate. No code is changed and no PR is opened.

Use this as the first step of a feature or design-sensitive playbook so a human — or a later gate — can review the plan before engineering effort is committed. For a defect whose cause is unknown, use Root Cause Analysis instead: that workflow reproduces the failure and traces the cause, whereas this one plans the build.

Steps

  1. 1.
    Open a terminal
    title
    Agent: SE Plan
    cwd
    {{entry_path}}
    terminal.open
  2. 2.
    Run a terminal command
    cmd
    |
    terminal.run

Workflow definition

schema_version: 1
id: agent_se_plan
title: "Investigate + Plan"
description: "Read-only: investigate the ticket and draft a concrete work plan — no code changes, no PR"
overview: |
  A read-only planning pass for any ticket — feature, refactor, or task — that produces an implementation plan before any code is written. The software engineer agent reads the ticket and the relevant code, configs, schemas, and any linked PRs, designs, or mockups, then posts a concrete work plan: the goal and acceptance criteria, the approach and key files to change, an ordered step checklist, risks and edge cases, a test strategy, and a complexity estimate. No code is changed and no PR is opened.

  Use this as the first step of a feature or design-sensitive playbook so a human — or a later gate — can review the plan before engineering effort is committed. For a defect whose cause is unknown, use Root Cause Analysis instead: that workflow reproduces the failure and traces the cause, whereas this one plans the build.

category:
  level: pipeline
  domain: engineering

metadata:
  agent: true
  role: se

params:
  ticket_url:
    type: string
    description: "Jira ticket URL"
  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: SE Plan"
    cwd: "{{entry_path}}"
  - type: terminal.run
    cmd: |
      source ~/.agent-env && claude --dangerously-skip-permissions "$(cat <<'SB_PROMPT'
      read ticket with attachments and all comments - {{ticket_url}}. if it fails, stop and report the error.
      this is a READ-ONLY planning pass: make NO code changes, run NO migrations, open NO PR.
      learn the relevant area first - read the affected code, configs, schemas, and any linked PRs / designs / mockups; reproduce current behaviour only if it helps scope the work.
      then draft a concrete WORK PLAN to deliver this ticket:
        - GOAL: the outcome + acceptance criteria (one line each)
        - APPROACH: implementation strategy + key files/modules to change (file:line where known)
        - STEPS: an ordered, reviewable checklist of the edits to make
        - RISKS: edge cases, what could break, backward-compatibility concerns
        - TESTS: which tests / QA verify it (new + existing)
        - ESTIMATE: complexity (S/M/L) + rough effort
      {{hint}}
      post ONE comment to the ticket with the work plan in the sections above. do not modify code or open a PR.
      SB_PROMPT
      )"