efficient-multi-agent-research
/efficient-multi-agent-research
Use when investigating, auditing, or reviewing more than 6 items across a codebase - function call sites, pattern usage, file reviews, or any research task with partitionable items that would pollute the main agent's context if read directly" # source: claude-plugin/skills/efficient-multi-agent-research/SKILL.md # generated-by: scripts/sync-skills.sh
- Author
- leonletto ↗
- Repository
- thrum ↗
- Licence
- MIT
- Last repository change
- 23.06.2026
Assessment and security
- Files in this package
- 2
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 23.06.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Use when investigating, auditing, or reviewing more than 6 items across a codebase - function call sites, pattern usage, file reviews, or any research task with partitionable items that would pollute the main agent's context if read directly" # source: claude-plugin/skills/efficient-multi-agent-research/SKILL.md # generated-by: scripts/sync-skills.sh
Triggers from the description
Original author description
Use when investigating, auditing, or reviewing more than 6 items across a codebase - function call sites, pattern usage, file reviews, or any research task with partitionable items that would pollute the main agent's context if read directly" # source: claude-plugin/skills/efficient-multi-agent-research/SKILL.md # generated-by: scripts/sync-skills.sh
How it works
- Efficient Multi-Agent Research
SKILL.md preview
---
name: efficient-multi-agent-research
description:
"Use when investigating, auditing, or reviewing more than 6 items across a
codebase - function call sites, pattern usage, file reviews, or any research
task with partitionable items that would pollute the main agent's context if
read directly"
# source: claude-plugin/skills/efficient-multi-agent-research/SKILL.md
# generated-by: scripts/sync-skills.sh
---
## Efficient Multi-Agent Research
### Overview
When investigating N items (N > 6), reading everything into the main agent's
context pollutes it and degrades decision-making. Instead, partition the work
across parallel sub-agents that write findings to disk, then consolidate into a
single report.
**Core principle:** The coordinator decides, sub-agents investigate. Keep
investigation results out of the main context until consolidated.
**REQUIRED BACKGROUND:** You MUST understand
superpowers:dispatching-parallel-agents before using this skill. That skill
covers general parallel dispatch. This skill extends it with a specific research
workflow: partition, investigate to disk, consolidate, then decide.
### When to Use
**Use when:**
- Investigating many call sites of a function (N > 6)
- Auditing usage of a pattern across a codebase
- Reviewing multiple files for a common issue
- Any research task with partitionable items
**Don't use when:**
- Simple searches (just use Grep/Glob)
- Tasks with 6 or fewer items (single agent is fine)
- Deeply interdependent items that can't be partitioned cleanly
### Core Pattern
#### Partition > Parallel Investigate > Consolidate > Decide
1. **Create output directory:** `mkdir -p dev-docs/<topic>/` — if re-running,
archive previous `findings_*.md` to a subdirectory (e.g., `run-01/`) before
starting so the consolidation glob only picks up current results.
2. **Launch investigation agents** — all in one message, all
`run_in_background=true`:
```text
Agent(run_in_background=true,
prompt="Investigate items A-D. Write to dev-docs/<topic>/findings_1.md
using table schema: [columns]. Flag uncertainties.")
Agent(run_in_background=true,
prompt="Investigate items E-H. Write to dev-docs/<topic>/findings_2.md ...")
```
Specify exact table columns and consistent formatting in every prompt.
3. **Wait** for all background agents to complete.
4. **Launch consolidation agent** — always request these four elements:
```text
Agent(prompt="Read all dev-docs/<topic>/findings_*.md.
Create consolidated_report.md with:
1. Unified table merging all agent tables
2. Cross-cutting patterns across findings
3. Summary statistics (e.g., '12/17 need fixes')
4. Prioritized recommendations")
```
5. **Review only `consolidated_report.md`** — never read individual findings
files into the main context.
### Quick Reference
| Aspect | Guidance |
| ------------- | --------------------------------------------------------- |
| Group size | 4-5 items per agent |
| Agent count | Typically 3-5 |
| Agent mode | Always `run_in_background=true` |
| Output | `dev-docs/<topic>/findings_N.md` per agent |
| Consolidation | Always a dedicated agent writing `consolidated_report.md` |
### Model Selection
Research dispatches almost always want `sonnet` (sometimes `haiku` for pure
mechanical gather-and-tabulate work). Opus is rarely justified for research —
the investigation prompts are narrow and the output is tabular, so frontier
reasoning buys nothing.
Every `Agent` dispatch must pass `model` explicitly; never let sub-agents
inherit the parent (often Opus) by default. See
`~/.claude/CLAUDE.md § Sub-Agent Model Selection` for the full tier table and
decision rule.
### Common Mistakes
**Skipping consolidation** - Reading 4 separate findings files into main context
defeats the entire purpose. Always launch a consolidation agent.
**Groups too large** - More than 5 items per agent gives diminishing returns.
Partition further.
**Using foreground agents** - Blocks the main agent and loses parallelism.
Always use `run_in_background=true`.
**Reading intermediate files** - The main agent should only read the
consolidated report, never individual findings files.
**Not specifying output format** - Agents produce inconsistent formats that are
hard to consolidate. Specify table columns in every prompt.
**Not specifying output file paths** - Agents may write to the working directory
or not at all. Always include the exact output path in every prompt.
### Example: Auditing 17 Call Sites
**Task:** Investigate 17 call sites of `resolveLocalAgentID()`
**Partition:** 4 agents (4-5 call sites each, grouped by source file)
**Table schema specified in every prompt:**
| Line | Command | How ID Is Used | Behavior for 0/1/multiple | Needs Fix? |
| ---- | ------- | -------------- | ------------------------- | ---------- |
**Result:** Main context stayed clean. Consolidation agent identified
cross-cutting pattern: "8/17 calls use identity for message filtering." Final
report provided prioritized recommendations.
### Variations
| Variant | When | How |
| ------------- | -------------------------------------- | ------------------------------------------------------------------------- |
| **Quick** | Items are independent, output is small | Lightweight consolidation: brief merged summary instead of full synthesis |
| **Deep** | Very large N (50+) | Multi-level: 8 agents > 2 meta-agents > 1 final report |
| **Iterative** | Need to refine criteria | Run first pass, update prompts based on patterns, re-run |
### See Also
- `adversarial-critique` — decision-shaped sister pattern. Use this skill when
investigating _what's there_ across N>6 items; use `adversarial-critique` when
deciding _which option wins_ among 2-3 design forks.
Files in this package (2)
- SKILL.md 6 KB
- agents/openai.yaml 1 KB
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · leonletto/thrum | 100 | MIT |
| leonletto/thrum | 100 | MIT |
Database snapshot: 13.11.2026 · package version f80b6a37f95d (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100researcher-investigating
Use when investigating, exploring code, working on a research task, when asked to find me X, or to investigate Y. Loads researcher-specific discipline for running an investigation cleanly." # source: claude-plugin/skills/researcher-investigating/SKILL.md # generated-by: scripts/sync-skills.sh - 100kastell-research
Read-only Kastell codebase exploration. Use when tracing a bug across files, mapping callsites before refactoring, or exploring unfamiliar subsystems. Runs in isolated context with Explore agent. - 100design-pattern-implementation
Reviews how design patterns are used or misused across the codebase and where patterns would help. Use when evaluating architecture, pattern fit, or over-engineering.