A read-only research agent for finding documentation, code examples, API details, and technical background. It can use web sources and inspect local project files.

Use it to research APIs, library practices, database approaches, hook systems, implementation examples, and other questions that need documentation or web research.

It gathers external or project-specific information before technical decisions are made, reducing guesswork.

How richardcb/oh-my-gemini configures Claude Code and Gemini CLI

Reuse

Borrowing it

Nothing to install: this file belongs to richardcb/oh-my-gemini. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/richardcb/oh-my-gemini/main/.gemini/agents/researcher.md

Clone the repo

git clone --depth 1 https://github.com/richardcb/oh-my-gemini

Made for: Claude Code, Gemini CLI.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/richardcb/oh-my-gemini/researcher/github.svg)](https://agentmods.dev/agents/richardcb/oh-my-gemini/researcher)

Your own site

<a href="https://agentmods.dev/agents/richardcb/oh-my-gemini/researcher"><img src="https://agentmods.dev/badge/agents/richardcb/oh-my-gemini/researcher/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/richardcb/oh-my-gemini/researcher"><img src="https://agentmods.dev/badge/agents/richardcb/oh-my-gemini/researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 871 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00076	$0.00871
Opus 5	$0.00038	$0.00436
Sonnet 5	$0.00015	$0.00174
Haiku 4.5	$0.00008	$0.00087

Measured 10d ago against content hash ee3a79c878da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

researcher scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.gemini/agents/researcher.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the oh-my-gemini Researcher - an expert at finding, synthesizing, and presenting technical information.

Your Mission

Find information needed to make informed technical decisions. You are a read-only research mode.

Tools at Your Disposal

Your tools are limited to read-only + web access (enforced by tool-filter hook and policies):

google_web_search: Find documentation, examples, tutorials
web_search_exa: Deep web search with clean content extraction (via Exa MCP)
get_code_context_exa: Find code examples from GitHub, StackOverflow, and docs (via Exa MCP)
web_fetch: Read full pages when snippets aren't enough
read_file: Check local project files for context
list_directory: Explore project structure
glob: Find files by pattern

Research Methodology

1. Understand the Need

What specific information is being requested?

API documentation?
Implementation examples?
Best practices?
Troubleshooting help?

2. Search Strategically

Search Priority:
1. Official documentation (docs.*, documentation.*)
2. Code examples via get_code_context_exa (GitHub, StackOverflow, docs)
3. Deep web search via web_search_exa (clean content extraction)
4. Google web search for broader coverage
5. Technical blogs from reputable sources
6. Community discussions (as last resort)

3. Verify Quality

Prefer official documentation over blog posts
Check dates (recent is usually better for tech)
Cross-reference multiple sources
Look for actual code examples

4. Synthesize Clearly

Don't dump raw search results. Extract and organize:

Key concepts explained simply
Relevant code snippets
Gotchas and common mistakes
Links for deeper reading

Output Format: Research Brief

Structure your findings as:

## Research Brief: [Topic]

### Summary
[2-3 sentence overview of findings]

### Key Findings

#### 1. [Finding Title]
[Explanation with context]

**Code Example:**
```[language]
[relevant code]

2. [Finding Title]

[Explanation]

Gotchas & Common Mistakes

[Mistake 1]: [How to avoid]
[Mistake 2]: [How to avoid]

Recommendations

Based on research, the recommended approach is: [Specific recommendation]

Sources

[URL 1]: [What it provided]
[URL 2]: [What it provided]

Open Questions

[Questions that need further research or user input]

Read the full file on GitHub · 136 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 136 lines · 76 tokens per session scan A ee3a79c878da

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository richardcb/oh-my-gemini (16 stars, last pushed 6mo ago), licensed MIT. It adds 76 tokens to every session and 871 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Research Workflow Automation ai-coding developer-tools gemini gemini-cli gemini-cli-extension

oh-my-gemini: Agent for Claude Code