msd-core/get-shit-done/workflows/research-phase.md at d137ce86ec29d7fcd8cfc975982f75d8802fa9ca

Files

Tom Boucher 8f2ec0e8f7 fix: add explicit wait-for-subagent instructions in orchestration workflows (#2755 )

Adds ORCHESTRATOR RULE blockquotes immediately after every Task() spawn
in 26 GSD workflow files, instructing the parent orchestrator to stop
working on the task while the subagent is active. This prevents the
parallel-work anti-pattern on Codex runtime where the parent continues
reading files and producing duplicate/conflicting output after spawning.

Rules are placed inline at each spawn point (not as generic headers)
so they are adjacent to and unambiguously associated with each Task()
call. Background Task() spawns get a variant noting not to return to
the spawning context until the subagent reports back.

Closes #2729

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-04-26 13:33:35 -04:00

2.5 KiB

Raw Blame History

Research how to implement a phase. Spawns gsd-phase-researcher with phase context.

Standalone research command. For most workflows, use /gsd-plan-phase which integrates research automatically.

<available_agent_types> Valid GSD subagent types (use exact names — do not fall back to 'general-purpose'):

gsd-phase-researcher — Researches technical approaches for a phase </available_agent_types>

Step 0: Resolve Model Profile

@~/.claude/get-shit-done/references/model-profile-resolution.md

Resolve model for:

gsd-phase-researcher

Step 1: Normalize and Validate Phase

@~/.claude/get-shit-done/references/phase-argument-parsing.md

PHASE_INFO=$(gsd-sdk query roadmap.get-phase "${PHASE}")

If found is false: Error and exit.

Step 2: Check Existing Research

ls .planning/phases/${PHASE}-*/RESEARCH.md 2>/dev/null || true

If exists: Offer update/view/skip options.

Step 3: Gather Phase Context

INIT=$(gsd-sdk query init.phase-op "${PHASE}")
if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
# Extract: phase_dir, padded_phase, phase_number, state_path, requirements_path, context_path
AGENT_SKILLS_RESEARCHER=$(gsd-sdk query agent-skills gsd-phase-researcher)

Step 4: Spawn Researcher

Task(
  prompt="<objective>
Research implementation approach for Phase {phase}: {name}
</objective>

<files_to_read>
- {context_path} (USER DECISIONS from /gsd-discuss-phase)
- {requirements_path} (Project requirements)
- {state_path} (Project decisions and history)
</files_to_read>

${AGENT_SKILLS_RESEARCHER}

<additional_context>
Phase description: {description}
</additional_context>

<output>
Write to: .planning/phases/${PHASE}-{slug}/${PHASE}-RESEARCH.md
</output>",
  subagent_type="gsd-phase-researcher",
  model="{researcher_model}"
)

ORCHESTRATOR RULE — CODEX RUNTIME: After calling Task() above, stop working on this task immediately. Do not read more files, edit code, or run tests related to this task while the subagent is active. Wait for the subagent to return its result. This prevents duplicate work, conflicting edits, and wasted context. Only resume when the subagent result is available.

Step 5: Handle Return

## RESEARCH COMPLETE — Display summary, offer: Plan/Dig deeper/Review/Done
## CHECKPOINT REACHED — Present to user, spawn continuation
## RESEARCH INCONCLUSIVE — Show attempts, offer: Add context/Try different mode/Manual

2.5 KiB Raw Blame History