8f2ec0e8f7
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>
85 lines
2.5 KiB
Markdown
85 lines
2.5 KiB
Markdown
<purpose>
|
|
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.
|
|
</purpose>
|
|
|
|
<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>
|
|
|
|
<process>
|
|
|
|
## 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
|
|
|
|
```bash
|
|
PHASE_INFO=$(gsd-sdk query roadmap.get-phase "${PHASE}")
|
|
```
|
|
|
|
If `found` is false: Error and exit.
|
|
|
|
## Step 2: Check Existing Research
|
|
|
|
```bash
|
|
ls .planning/phases/${PHASE}-*/RESEARCH.md 2>/dev/null || true
|
|
```
|
|
|
|
If exists: Offer update/view/skip options.
|
|
|
|
## Step 3: Gather Phase Context
|
|
|
|
```bash
|
|
INIT=$(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
|
|
|
|
</process>
|