/research-phase
Research how to implement a phase (standalone — usually use /pbr:plan-phase instead)
$ npx -y skills add SienkLogic/plan-build-run --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/research-phase
Context preview
What this command does when you run it.
Research how to implement a phase (standalone — usually use /pbr:plan-phase instead)
Command definition
research-phase.mddescription: "Research how to implement a phase (standalone — usually use /pbr:plan-phase instead)"
argument-hint: "[phase]"
allowed-tools:
- Read
- Bash
- Task
<objective> Research how to implement a phase. Spawns researcher agent with phase context.
**Note:** This is a standalone research command. For most workflows, use `/pbr:plan-phase` which integrates research automatically.
**Use this command when:**
- You want to research without planning yet
- You want to re-research after planning is complete
- You need to investigate before deciding if a phase is feasible
</objective>
<context> Phase number: $ARGUMENTS (required)
@.planning/ROADMAP.md @.planning/STATE.md </context>
<process>
1. Validate Phase
PHASE_INFO=$(pbr-tools roadmap get-phase "$ARGUMENTS")
Error if phase not found. Extract phase_number, phase_name, goal.
2. Check Existing Research
Look for `.planning/phases/{NN}-*/RESEARCH.md`. If exists, offer: 1) Update research, 2) View existing, 3) Skip.
3. Gather Context
Read phase description, requirements, and prior decisions.
4. Spawn Researcher
Task({
subagent_type: "pbr:researcher",
prompt: "Research implementation approach for Phase {N}: {name}\n\nPhase goal: {goal}\nRequirements: {requirements}\nPrior decisions: {decisions}\n\nWrite to: .planning/phases/{NN}-{slug}/{NN}-RESEARCH.md"
})5. Handle Return
- `## RESEARCH COMPLETE`: Display summary, offer `/pbr:plan-phase {N}`
- `## RESEARCH INCONCLUSIVE`: Show what was attempted, offer options
</process>
Read more
description: "Research how to implement a phase (standalone — usually use /pbr:plan-phase instead)" argument-hint: "[phase]" allowed-tools: - Read - Bash - Task
<objective> Research how to implement a phase. Spawns researcher agent with phase context.
**Note:** This is a standalone research command. For most workflows, use `/pbr:plan-phase` which integrates research automatically.
**Use this command when:**
- You want to research without planning yet
- You want to re-research after planning is complete
- You need to investigate before deciding if a phase is feasible
</objective>
<context> Phase number: $ARGUMENTS (required)
@.planning/ROADMAP.md @.planning/STATE.md </context>
<process>
1. Validate Phase
PHASE_INFO=$(pbr-tools roadmap get-phase "$ARGUMENTS")
Error if phase not found. Extract phase_number, phase_name, goal.
2. Check Existing Research
Look for `.planning/phases/{NN}-*/RESEARCH.md`. If exists, offer: 1) Update research, 2) View existing, 3) Skip.
3. Gather Context
Read phase description, requirements, and prior decisions.
4. Spawn Researcher
Task({
subagent_type: "pbr:researcher",
prompt: "Research implementation approach for Phase {N}: {name}\n\nPhase goal: {goal}\nRequirements: {requirements}\nPrior decisions: {decisions}\n\nWrite to: .planning/phases/{NN}-{slug}/{NN}-RESEARCH.md"
})5. Handle Return
- `## RESEARCH COMPLETE`: Display summary, offer `/pbr:plan-phase {N}`
- `## RESEARCH INCONCLUSIVE`: Show what was attempted, offer options
</process>
Plan it. Build it. Run it. A Claude Code plugin for structured development with context-engineered agents.
Repo: SienkLogic/plan-build-run
Other commands on plan-build-run.
- /add-phase
Add phase to end of current milestone in roadmap
Open command - /add-todo
Capture idea or task as todo from current conversation context
Open command - /audit-fix
Run audit, prioritize findings, auto-fix via quick tasks, test, and commit.
Open command - /audit-milestone
Audit milestone completion against original intent before archiving
Open command - /audit
Review past Claude Code sessions for PBR workflow compliance and UX quality.
Open command - /autonomous
Run multiple phases hands-free. Chains discuss, plan, build, and verify automatically.
Open command

