ap-plan

name	ap-plan
description	Turn 1-3 backlog problems into a small executable plan with 1:1 checks. Use to define the next safe step with clear tasks and verification, including multi-milestone scope when useful.

/ap:plan

Purpose

Turn backlog problems into a small, executable plan with explicit checks.

/ap:plan combines "discuss" + "plan" by forcing:

• surfaced decisions
• tight tasks
• check-first definition of done

---

Inputs

Any of the following:

• Backlog IDs (e.g. B001 B003)
• Milestone IDs (e.g. M01, or M01 M02 when cross-milestone planning is justified)
• A goal statement (e.g. "plan the next best step")
• Constraints or preferences (optional)

If no backlog IDs are provided, select the best next problems from BACKLOG.md using PROJECT.md success criteria and current STATUS.

---

Reads

Must consult:

• .agent-pack/core/context/PROJECT.md
• .agent-pack/core/context/DECISIONS.md
• .agent-pack/core/work/LOADOUT.md
• .agent-pack/core/work/BACKLOG.md
• .agent-pack/core/work/STATUS.md

May consult (if exists):

• .agent-pack/core/context/USERS.md (JTBD, goals, and success signals for user-facing work)
• .agent-pack/core/context/SECURITY.md (when planning auth, data handling, or compliance-sensitive work)
• .agent-pack/core/work/PLAN.md
• .agent-pack/core/work/CHECKS.md

---

Process

1. Select scope (small)
   • Choose 1-3 backlog items max.
   • Prefer the smallest coherent scope.
   • It is valid to plan across multiple milestones when dependencies or value justify it.
   • If planning across milestones, state why.
   • State why they are chosen now.
2. Write the plan goal
   • A concrete state change.
3. Create a context snapshot
   • Pull only the constraints/decisions relevant to this plan.
   • Pull relevant module/loadout constraints from LOADOUT.md.
   • Consult USERS.md and SECURITY.md when they are relevant to scope.
4. Surface decisions needed
   • Identify ambiguity that could cause rework.
   • For each decision: list options + safe default + who must decide.
5. Produce tasks (1-5)
   • Each task must be atomic, executable, and bounded.
   • Each task must declare:
   • Scope boundary
   • Touch points (files/areas)
   • Done-when condition
6. Define checks (1:1)
   • For every task, define exactly one check.
   • Checks must be observable + repeatable.
7. Declare out-of-scope
   • List items explicitly not handled in this plan.
8. Update status
   • Set Current focus and Next 3 actions.
   • The first next action should usually be /ap:do T001.

---

Output rules

• Follow .agent-pack/core/context/OUTPUT-CONTRACTS.md.
• Follow .agent-pack/core/context/PLANNING-RULES.md.
• Prefer clarity over completeness.
• If uncertainty is high, reduce plan scope rather than adding complexity.
• When listing milestones, backlog items, tasks, or checks in chat output, always include ID and title in ID - Title format.
• Include a Suggested next steps section with 1-3 commands that naturally move into /ap:do.

---

Output contract

<Output-Structure>
### Files updated

- .agent-pack/core/work/PLAN.md -- <summary>
- .agent-pack/core/work/CHECKS.md -- <summary>
- .agent-pack/core/work/STATUS.md -- <summary>
- .agent-pack/core/context/DECISIONS.md -- <summary if changed>

### Decisions made

- DN###: <decision needed> -- <options + default>
- D###/P###: <any durable decision added>

### Tasks created or modified

- <task-id> - <task title> -- <what changed> -- check: <check-id> - <check title>

### Checks created or affected

- <check-id> - <check title> -- <what changed> -- task: <task-id> - <task title>

### Unknowns / needs input

- <questions>

### Suggested next steps

- /ap:do T### - <task title>
- /ap:do T### - <task title>

</Output-Structure>

---

Completion criteria

/ap:plan is complete when:

• PLAN.md contains:
• a plan goal
• scope links to backlog (milestone(s) and backlog items in scope; guidance-level, not strict schema)
• context snapshot
• decisions needed (may be empty)
• 1-5 tasks
• out-of-scope list
• CHECKS.md contains exactly one check per task
• STATUS.md next actions point to executing the plan

If any of these are missing, the command must report it.

---

Common failure modes

• Too many tasks (plan is too big)
• Tasks without clear scope boundaries
• Checks that restate tasks instead of verifying outcomes
• Hiding decisions inside tasks
• Planning implementation without stating the problem being solved

---

Notes

A good plan should be boring.

If the plan feels exciting, it is probably too ambitious.