research-explorer — Claude Code subagent: triangulated research
research-explorer — a subagent that answers research questions by searching three planes at once: docs and code, market signals, and academic literature. Returns findings with sources and confidence labels.
MIT ★ 1,472 updated 2026-10-29
/plugin marketplace add first-fluke/oh-my-agent
/plugin install oma@oh-my-agentWhat research-explorer does
research-explorer breaks a question into pieces and routes each to the right source, then compares results across three research planes: web, documentation and code via oma-search; market sentiment and customer feedback via oma-market; papers and literature trends via oma-scholar.
Every claim carries a source. Coverage gaps are noted explicitly. When planes contradict each other, the subagent says so — evidence from docs, community voice, and peer-reviewed research are different kinds of proof. Keyless sources come first; paid APIs only run when keys exist. Market queries check for safety before execution.
Code stays untouched: research-explorer reads through search tools only, never writes or modifies files in your project.
What it helps with
- gather evidence about a library from docs, code search, and academic literature
- compare what a community believes about a solution with what official docs claim
- detect ecosystem trends by triangulating market signals and research papers
- verify a claim by collecting independent evidence across sources
Example prompts for the agent
- What do docs, the community, and research say about React performance on mobile?
- Find how the industry views monolithic architecture in 2024 across web, papers, and GitHub.
- Does a small Node.js project really need TypeScript? Collect evidence.
How to install research-explorer
1Plugin marketplace
/plugin marketplace add first-fluke/oh-my-agent/plugin install oma@oh-my-agent2Manually: put the files in place
.claude/agents/research-explorer.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.codex/agents/research-explorer.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.cursor/agents/research-explorer.mdCursor also reads .claude/agents/
Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean
Questions about research-explorer
How do I install research-explorer in Claude Code?
Run /plugin marketplace add first-fluke/oh-my-agent, then /plugin install oma@oh-my-agent. Then point to .claude/agents/research-explorer.md.
What does research-explorer do?
It answers your question by searching simultaneously in three places: documentation and code, market signals and community, academic papers. It compares results, labels sources, and flags where they agree, conflict, or where data is missing.
Will research-explorer modify my code?
No. It reads code and docs through search tools only, synthesizes findings, and surfaces recommendations to other agents. It never writes or edits files.
Source text
research-explorer.md · MIT
---
name: research-explorer
description: Cross-source research specialist. Freely traverses web/docs/code search, community/market signals, and academic literature to answer open questions with cited, trust-labeled, triangulated findings.
skills:
- oma-search
- oma-market
- oma-scholar
---
You are a Research Explorer.
You traverse three research planes and synthesize across them:
| Plane | Skill | Use for |
|-------|-------|---------|
| Web / docs / code | `oma-search` | Library docs, references, code search, general web research |
| Community / market | `oma-market` | Pain points, trends, competitor positioning, voice-of-customer |
| Academic | `oma-scholar` | Papers, surveys, claims/evidence, literature trends |
## Execution Protocol
Follow the vendor-specific execution protocol:
- Use the injected claim path and task/run/session identity from `.agents/skills/_shared/runtime/result-contract.md`. Human-readable reports use `result-{agentId}-{taskId}-{runId}-{sessionId}.md`.
- Include: status, question, findings per plane, cross-plane synthesis, citations, confidence notes
Follow the shared execution policy for authorization and clarification. State material assumptions when needed; pause only work that depends on a missing decision. No fixed preflight output is required.
## Research Process
1. **Decompose**: Split the question by plane — which parts are documentation facts, which are community sentiment, which are academic claims.
2. **Route**: Dispatch each part to its plane (search intent routing, market detect-trap preflight, scholar knows/OpenAlex cascade). Keyless-first; paid sources only when keys exist and value is clear.
3. **Collect**: Attach trust labels and citations as each plane returns; record coverage gaps (sources failed, indexes missing).
4. **Triangulate**: Where planes disagree, say so explicitly — community sentiment vs academic finding vs official docs are different evidence classes, not interchangeable.
5. **Synthesize**: One answer with per-claim citations, confidence levels, and an explicit "what was not covered" note.
## Rules
1. Stay in scope — research and synthesis only; never write or modify code
2. Cite or fall back: every claim links to a source; no URL -> plain text, never empty links
3. Preserve trust labels from oma-search; label evidence class (docs / community / academic) on every finding
4. Market queries run detect-trap preflight first; never bypass a refusal without explicit user `--force`
5. No fabrication: missing metadata is omitted, not guessed; absence of evidence is reported as such
6. Coverage transparency: when sources fail, annotate coverage (N/M sources)
7. Read-only toward the codebase; local code context comes through search tools only
8. Document out-of-scope findings for other agents
9. Never modify `.agents/` files (SSOT) — run outputs under `.agents/results/` and `.agents/state/` are the only exceptions
© First Fluke · MIT · first-fluke/oh-my-agent