| name | quick-plan |
| description | Enter planning mode with AI SDLC standards awareness |
Planning Mode with Standards Awareness
Enter Google Antigravity CLI's planning mode for a task, with automatic discovery of project standards from .agyflow/docs/.
Usage
/agyflow:quick-plan [task description]
Examples
/agyflow:quick-plan "Add user authentication with email/password"
/agyflow:quick-plan "Refactor the payment processing module"
/agyflow:quick-plan
Workflow
Step 1: Parse Input
Get the task description:
Step 1b: Create Task Directory
Create a lightweight task directory for artifact anchoring.
- Generate a task name from the task description:
- Extract 3–5 key words, convert to lowercase kebab-case
- Prepend today's date:
YYYY-MM-DD-kebab-name
- Examples: "Add retry logic to API client" →
2026-05-28-add-api-retry-logic, "Refactor the payment processing module" → 2026-05-28-refactor-payment-module
- Create directory:
.agyflow/tasks/quick-plan/YYYY-MM-DD-task-name/
- Create
analysis/ subdirectory inside it
- Write
task.yml with initial state using the template src/templates/quick-plan-task.yml.
Step 2: Discover and Read Standards (BEFORE Plan Mode)
CRITICAL: This step MUST complete before calling Plan Agent.
-
Check if .agyflow/docs/INDEX.md exists
- If not exists: Note that no standards are available, skip to Step 3
- If exists: Continue with discovery below
-
Read INDEX.md to understand available standards and documentation
-
Identify applicable standards based on:
- The categories and files listed in INDEX.md
- The nature of the task being planned
- Keywords and patterns in the task description (e.g., "API" → api standards, "form" → validation standards, "upload" → file-handling standards)
-
READ the actual standard files using the Read tool — reading INDEX.md alone is NOT sufficient
-
Summarize key guidelines from each standard file read — these will carry into plan mode as context
-
Update task.yml: Add paths of standards read to standards_applied list
Step 2b: Write Findings
After standards discovery, write analysis/findings.md in the task directory:
# Task Analysis
## Context
[What was analyzed to inform the plan — codebase areas explored, existing patterns found]
## Key Decisions
[Architectural or implementation decisions made during planning]
## Standards Referenced
- [standard file]: [key guideline applied]
Step 3: Enter Planning Mode
Use the Plan agent to trigger Google Antigravity CLI's builtin planning mode.
Standards context from Step 2 MUST actively inform all plan mode phases:
- Phase 1 (Explore): When launching Explore agents, include in the prompt: "The following project standards apply to this task: [list standard files and key guidelines from Step 2]. Verify how the existing codebase follows these standards."
- Phase 2 (Plan): When launching Plan agents, include in the prompt: "Apply these project standards in your implementation plan: [list standard files and key guidelines from Step 2]. Each implementation step must conform to these standards."
- Phase 4 (Final Plan): The plan file must incorporate standards into the implementation steps themselves, not just list them in a separate section.
The planning mode will:
- Launch Explore agents to understand the codebase (with standards context)
- Launch Plan agents to design implementation approach (with standards constraints)
- Review and verify alignment with user intent
- Write final plan to plan file (with standards woven into steps)
- Ask for user approval (gated on mandatory standards sections)
Approval question gate: Mandatory Standards Sections
BLOCKING: Do NOT call ask user for approval until the plan file contains these sections:
-
"## Applicable Standards" — list each standard file that was read, with key guidelines extracted from each. If no standards exist, state: "No AI SDLC standards found. Consider running /agyflow:flow-init."
-
"## Standards Compliance Checklist" — checkboxes for each applicable standard guideline that implementation must follow. Example:
- [ ] API endpoints follow REST naming conventions (from `standards/backend/api.md`)
- [ ] Error responses use standard error format (from `standards/backend/api.md`)
- [ ] New components use TypeScript strict mode (from `standards/frontend/components.md`)
If these sections are missing from the plan file, add them before asking user for approval.
Graceful Fallback
If .agyflow/docs/ does not exist:
Continue with planning mode normally. The "Applicable Standards" section in the plan should note:
No AI SDLC standards found. Consider running `/agyflow:flow-init` to initialize
project documentation and coding standards for better consistency.
What This Does
- Parses task description from user input
- Creates lightweight task directory with
task.yml for artifact anchoring
- Discovers and READS applicable standard files from
.agyflow/docs/ (BEFORE plan mode)
- Writes
analysis/findings.md with task context and key decisions
- Enters Google Antigravity CLI's builtin planning mode via delegating to
Plan Agent with standards already loaded
- Produces a plan file with implementation approach, applicable standards, and compliance checklist
- Gates Approval question on mandatory standards sections in the plan file
- Updates
task.yml with status: completed and plan_path after plan approval
Benefits Over Manual Planning
- Automatic standards discovery and integration
- Standards read BEFORE planning begins (not as an afterthought)
- Plan file for review before implementation
- Standards compliance checklist built into the plan
After Planning
Once the plan is approved:
- Update
task.yml: set status: completed, plan_path: [path to plan file], updated: [now]
- Implementation begins based on the plan
- Standards are applied during coding
Post-Implementation Verification
After implementation is complete, verify standards compliance using the checklist from the plan:
- Review the "Standards Compliance Checklist" in the plan file
- For each checklist item: verify implementation follows the guideline
- Document verification results (pass/fail for each item)
- Address any violations before marking task complete
This ensures the discovered standards are actually enforced, not just documented.