kata-research-phase

<objective> Research how to implement a phase. Spawns kata-phase-researcher agent with phase context.

Note: This is a standalone research command. For most workflows, use /kata-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

Orchestrator role: Parse phase, validate against roadmap, check existing research, gather context, spawn researcher agent, present results.

Why subagent: Research burns context fast (WebSearch, Context7 queries, source verification). Fresh 200k context for investigation. Main context stays lean for user interaction. </objective>

<context> Phase number: $ARGUMENTS (required)

Normalize phase input in step 1 before any directory lookups. </context>

<process>

0. Resolve Model Profile

Read model profile for agent spawning:

MODEL_PROFILE=$(node scripts/kata-lib.cjs read-config "model_profile" "balanced")

Default to "balanced" if not set.

Model lookup table:

Store resolved model for use in Task calls below.

1. Normalize and Validate Phase

# Normalize phase number (8 → 08, but preserve decimals like 2.1 → 02.1)
if [[ "$ARGUMENTS" =~ ^[0-9]+$ ]]; then
  PHASE=$(printf "%02d" "$ARGUMENTS")
elif [[ "$ARGUMENTS" =~ ^([0-9]+)\.([0-9]+)$ ]]; then
  PHASE=$(printf "%02d.%s" "${BASH_REMATCH[1]}" "${BASH_REMATCH[2]}")
else
  PHASE="$ARGUMENTS"
fi

grep -A5 "Phase ${PHASE}:" .planning/ROADMAP.md 2>/dev/null

If not found: Error and exit. If found: Extract phase number, name, description.

2. Find Phase Directory and Check Existing Research

# Universal phase discovery
PADDED=$(printf "%02d" "$PHASE" 2>/dev/null || echo "$PHASE")
PHASE_DIR=""
for state in active pending completed; do
  PHASE_DIR=$(find .planning/phases/${state} -maxdepth 1 -type d -name "${PADDED}-*" 2>/dev/null | head -1)
  [ -z "$PHASE_DIR" ] && PHASE_DIR=$(find .planning/phases/${state} -maxdepth 1 -type d -name "${PHASE}-*" 2>/dev/null | head -1)
  [ -n "$PHASE_DIR" ] && break
done
# Fallback: flat directory (backward compatibility)
if [ -z "$PHASE_DIR" ]; then
  PHASE_DIR=$(find .planning/phases -maxdepth 1 -type d -name "${PADDED}-*" 2>/dev/null | head -1)
  [ -z "$PHASE_DIR" ] && PHASE_DIR=$(find .planning/phases -maxdepth 1 -type d -name "${PHASE}-*" 2>/dev/null | head -1)
fi

ls ${PHASE_DIR}/RESEARCH.md 2>/dev/null

If exists: Offer: 1) Update research, 2) View existing, 3) Skip. Wait for response.

If doesn't exist: Continue.

3. Gather Phase Context

grep -A20 "Phase ${PHASE}:" .planning/ROADMAP.md
cat .planning/REQUIREMENTS.md 2>/dev/null
cat ${PHASE_DIR}/${PHASE}-CONTEXT.md 2>/dev/null
grep -A30 "### Decisions Made" .planning/STATE.md 2>/dev/null

Present summary with phase description, requirements, prior decisions.

3.5. Load Phase-Researcher Instructions

Read the phase-researcher agent instructions for inlining into Task() calls:

phase_researcher_instructions_content=$(cat references/phase-researcher-instructions.md)

4. Spawn kata-phase-researcher Agent

Research modes: ecosystem (default), feasibility, implementation, comparison.

<research_type>
Phase Research — investigating HOW to implement a specific phase well.
</research_type>

<key_insight>
The question is NOT "which library should I use?"

The question is: "What do I not know that I don't know?"

For this phase, discover:
- What's the established architecture pattern?
- What libraries form the standard stack?
- What problems do people commonly hit?
- What's SOTA vs what Claude's training thinks is SOTA?
- What should NOT be hand-rolled?
</key_insight>

<objective>
Research implementation approach for Phase {phase_number}: {phase_name}
Mode: ecosystem
</objective>

<context>
**Phase description:** {phase_description}
**Requirements:** {requirements_list}
**Prior decisions:** {decisions_if_any}
**Phase context:** {context_md_content}
</context>

<downstream_consumer>
Your RESEARCH.md will be loaded by `/kata-plan-phase` which uses specific sections:
- `## Standard Stack` → Plans use these libraries
- `## Architecture Patterns` → Task structure follows these
- `## Don't Hand-Roll` → Tasks NEVER build custom solutions for listed problems
- `## Common Pitfalls` → Verification steps check for these
- `## Code Examples` → Task actions reference these patterns

Be prescriptive, not exploratory. "Use X" not "Consider X or Y."
</downstream_consumer>

<quality_gate>
Before declaring complete, verify:
- [ ] All domains investigated (not just some)
- [ ] Negative claims verified with official docs
- [ ] Multiple sources for critical claims
- [ ] Confidence levels assigned honestly
- [ ] Section names match what phase-plan expects
</quality_gate>

<output>
Write to: ${PHASE_DIR}/${PHASE}-RESEARCH.md
</output>

Task(
  prompt="<agent-instructions>\n{phase_researcher_instructions_content}\n</agent-instructions>\n\n" + filled_prompt,
  subagent_type="general-purpose",
  model="{researcher_model}",
  description="Research Phase {phase}"
)

5. Handle Agent Return

## RESEARCH COMPLETE: Display summary.

Next steps: Offer: Plan phase, Dig deeper, Brainstorm ideas, Review full, Done.

• "Brainstorm ideas": Run /kata-brainstorm to explore ideas based on research findings. After brainstorm completes, return to this menu.

## CHECKPOINT REACHED: Present to user, get response, spawn continuation.

## RESEARCH INCONCLUSIVE: Show what was attempted, offer: Add context, Try different mode, Manual.

6. Spawn Continuation Agent

<objective>
Continue research for Phase {phase_number}: {phase_name}
</objective>

<prior_state>
Research file: @${PHASE_DIR}/${PHASE}-RESEARCH.md
</prior_state>

<checkpoint_response>
**Type:** {checkpoint_type}
**Response:** {user_response}
</checkpoint_response>

Task(
  prompt="<agent-instructions>\n{phase_researcher_instructions_content}\n</agent-instructions>\n\n" + continuation_prompt,
  subagent_type="general-purpose",
  model="{researcher_model}",
  description="Continue research Phase {phase}"
)

</process>

<success_criteria>

• Phase validated against roadmap
• Existing research checked
• kata-phase-researcher spawned with context
• Checkpoints handled correctly
• User knows next steps

</success_criteria>