feat: Add subagent usage guidance to refine and plan prompts

Instruct architect agents to leverage subagents for parallel work —
page analysis, codebase verification, dependency mapping, and pattern
discovery — instead of doing everything sequentially.
This commit is contained in:
Lukas May
2026-03-06 13:39:19 +01:00
parent e3246baf51
commit a0574a1ae9
2 changed files with 18 additions and 0 deletions

View File

@@ -81,6 +81,15 @@ Each phase must pass: **"Could a detail agent break this into tasks without clar
</examples> </examples>
</specificity> </specificity>
<subagent_usage>
Use subagents to parallelize your analysis — don't do everything sequentially:
- **Domain decomposition**: Spawn separate subagents to investigate different aspects of the initiative (e.g., one for database/schema concerns, one for API surface, one for frontend components) and synthesize their findings into your phase plan.
- **Dependency mapping**: Spawn a subagent to map existing code dependencies and file ownership while you analyze initiative requirements, so you can make informed decisions about phase boundaries and parallelism.
- **Pattern discovery**: When the initiative touches multiple subsystems, spawn subagents to search for existing patterns in each subsystem simultaneously rather than exploring them one at a time.
Don't spawn subagents for trivial initiatives with obvious structure — use judgment.
</subagent_usage>
<existing_context> <existing_context>
- Account for existing phases/tasks — don't plan work already covered - Account for existing phases/tasks — don't plan work already covered
- Always generate new phase IDs — never reuse existing ones - Always generate new phase IDs — never reuse existing ones

View File

@@ -33,6 +33,15 @@ Ignore style, grammar, formatting unless they cause genuine ambiguity. Rough but
If all pages are already clear, signal done with no output files. If all pages are already clear, signal done with no output files.
</improvement_priorities> </improvement_priorities>
<subagent_usage>
Use subagents to parallelize your work:
- **Parallel page analysis**: Spawn one subagent per page (or group of related pages) to analyze clarity issues simultaneously rather than reviewing pages sequentially.
- **Codebase verification**: When checking whether a requirement is feasible or matches existing patterns, spawn a subagent to search the codebase while you continue reviewing other pages.
- **Cross-reference validation**: Spawn a subagent to verify that all [[page:$id|title]] cross-references are valid and consistent across pages.
Don't over-split — if there are only 1-2 short pages, just do the work directly.
</subagent_usage>
<rules> <rules>
- Ask 2-4 questions if you need clarification - Ask 2-4 questions if you need clarification
- Preserve [[page:\$id|title]] cross-references - Preserve [[page:\$id|title]] cross-references