Create a plan

Execution reference: This page specifies the tool protocol for automation agents. For instructions to follow in Studio, use the user guide.

Create an implementation plan from the user's brief. The Studio starter saves a Markdown file when file tools are available.

Agent-facing flow

  1. If the Veryfront skill is not loaded, load it with veryfront__load_skill({ "skillId": "veryfront" }). Reuse an already-loaded skill.
  2. Read this guide through the documentation link or the reference reader exposed by your host. A reference path is not a tool name or a separate skill ID.
  3. If the request is broad, ask exactly one short veryfront__form_input with one required brief field. Continue from the submitted brief. The starter label does not supply the task.
  4. Inspect only the project files, routes, docs, and history needed to plan the requested work.
  5. Write a concise plan with outcome, scope, assumptions, steps, acceptance checks, risks, and stop condition. Include the requested lifecycle stages: plan, build, QA, deploy, run, operate, and improve. Omit stages outside the request.
  6. For the bare Studio "Create a plan" starter, save the plan as Markdown under plans/ with veryfront__create_file or veryfront__update_file when file tools are available. Choose a concise slug from the submitted brief for the file name.
  7. For other planning requests, save the plan when the user asks for a file or gives an exact path.

Guardrails

  • Do not load a removed plan sub-skill.
  • Do not delegate on the first turn just to acknowledge the starter prompt.
  • Do not treat the starter label, generic starter prompt, or storage location instruction as the work topic.
  • Do not ask for output paths, depth, mode, audience, or option fields by default.
  • Do not create app, page, route, or chat UI files for a planning-only request.
  • Do not finish the bare Studio starter with inline-only output when file tools are available.

Example pattern

This example plans a support-triage agent. Use the user's brief to choose the actual topic.

md
<!-- plans/support-triage-agent.md -->
# Plan: Support Triage Agent

## Outcome

Create an AI agent that reads incoming support requests, classifies severity, drafts a suggested reply, and escalates cases that need a human.

## Assumptions

- The agent can read support tickets through an approved integration.
- The agent drafts responses but does not send them automatically.
- High-risk or billing-related cases require human review.

## Steps

1. Define the agent goal, stop condition, and escalation rules.
2. Select the minimum required tools for listing, reading, and drafting ticket responses.
3. Add instructions for severity classification, reply drafting, and handoff notes.
4. Add a verification checklist with sample tickets for low, medium, and urgent cases.
5. Test that the agent refuses unsupported actions and asks for approval before state changes.

## Verification

- The agent classifies sample tickets consistently.
- Draft replies include evidence from the ticket.
- Escalation cases produce a concise human handoff summary.
- The agent never sends a message without explicit approval.
js
veryfront__create_file({
  "project_reference": "<project>",
  "path": "plans/support-triage-agent.md",
  "content": "# Plan: Support Triage Agent\n\n## Outcome\n\nCreate an AI agent that reads incoming support requests, classifies severity, drafts a suggested reply, and escalates cases that need a human.\n\n## Steps\n\n1. Define the agent goal, stop condition, and escalation rules.\n2. Select the minimum required tools for listing, reading, and drafting ticket responses.\n3. Add instructions for severity classification, reply drafting, and handoff notes.\n4. Add a verification checklist with sample tickets.\n5. Test refusal and approval behavior before state changes.\n"
})

The MCP call saves the Markdown in content at path. Before updating a plan, read it and use veryfront__update_file with the returned version or checksum when available.

Output shape

For the bare Studio starter, return the saved file path plus a short summary. For other planning requests, return the plan in the conversation unless the user requested a file.