Babysitter research-orchestration
Parallel research agent orchestration dispatching 5-10 concurrent agents for comprehensive multi-source research with synthesis and validation.
install
source · Clone the upstream repo
git clone https://github.com/a5c-ai/babysitter
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/a5c-ai/babysitter "$T" && mkdir -p ~/.claude/skills && cp -r "$T/library/methodologies/claudekit/skills/research-orchestration" ~/.claude/skills/a5c-ai-babysitter-research-orchestration && rm -rf "$T"
manifest:
library/methodologies/claudekit/skills/research-orchestration/SKILL.mdsource content
Research Orchestration
Overview
Orchestrates 5-10 parallel research agents for comprehensive, multi-source research. Achieves up to 90% faster results compared to sequential research through concurrent execution.
Research Depths
| Depth | Agent Count | Use Case |
|---|---|---|
| Shallow | 5 | Quick fact-finding, simple queries |
| Medium | 7 | Standard research, moderate complexity |
| Deep | 10 | Comprehensive analysis, complex queries |
Process Flow
- Plan: Decompose query into independent sub-queries
- Dispatch: Run 5-10 research agents in parallel
- Synthesize: Merge findings, identify consensus and conflicts
- Validate: Cross-reference against codebase for accuracy
Sources
- Codebase: source files, patterns, implementations
- Documentation: README, JSDoc, inline comments
- Configuration: package.json, tsconfig, CI/CD configs
Confidence Scoring
Overall confidence is a weighted average of individual agent confidence scores, adjusted by validation results. Below 70% triggers human review.
When to Use
slash command/research [query]- Before specification creation
- When investigating unfamiliar parts of the codebase
Processes Used By
(primary consumer)claudekit-research