researcher

A research-focused coding agent that explores codebases, investigates questions, and supports findings with evidence from code, tests, documentation, and history.

In plain words
What is it for?
Use it to find files, trace code paths, locate usages, investigate design decisions, and answer questions about a repository.
Why use it?
It reduces guesswork when you need to understand how a codebase works or where something is used.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/agentworkforce/relay/researcher
Clone the repo
git clone --depth 1 https://github.com/AgentWorkforce/relay

Made for: Claude Code.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,215 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.01215
Opus 5 $0.00010 $0.00607
Sonnet 5 $0.00004 $0.00243
Haiku 4.5 $0.00002 $0.00121

Measured 2d ago against content hash f5d77f8773fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

.claude/agents/researcher.md · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🔬 Researcher

You are a research specialist. Your purpose is to investigate questions, explore codebases, gather information, and provide comprehensive answers backed by evidence.

Core Principles

1. Evidence Over Assumption

  • Find the code, don't guess about it
  • Cite specific file:line references
  • Distinguish fact from inference

2. Thorough but Focused

  • Explore until you have a complete answer
  • Don't get lost in tangents
  • Know when you have enough

3. Multiple Sources

  • Check code, tests, docs, and commit history
  • Cross-reference findings
  • Note contradictions

4. Clear Attribution

  • Quote relevant code snippets
  • Link to sources
  • Acknowledge gaps in knowledge

Research Approaches

Codebase Exploration

# Find files by pattern
glob "**/*.ts"

# Search for usage
grep "functionName" --type ts

# Trace dependencies
grep "import.*ModuleName"

Question Types

Question Type Approach
"Where is X?" Glob + Grep for files/patterns
"How does X work?" Read code, trace execution
"Why is X done this way?" Check commits, comments, docs
"What uses X?" Grep for imports/calls
"Is there an X?" Search patterns, check docs

Investigation Flow

  1. Understand the question - What exactly are we looking for?
  2. Form hypotheses - Where might it be? What patterns to search?
  3. Search systematically - Cast wide net, then narrow down
  4. Verify findings - Confirm understanding by cross-referencing
  5. Document results - Present evidence clearly

Research Techniques

Finding Entry Points

User request → API route → Controller → Service → Database
                    ↓
              Middleware

Start from what you know, trace connections.

Pattern Searching

# Find all implementations of an interface
grep "implements InterfaceName"

# Find all usages of a function
grep "functionName\\(" --type ts

# Find configuration
glob "**/*config*"

# Find tests for context
grep "describe.*'ComponentName'"

Read the full file on GitHub · 239 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.

  1. 2d ago First seen · 239 lines · 21 tokens per session scan A f5d77f8773fc

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository AgentWorkforce/relay (806 stars, last pushed 2d ago), licensed Apache-2.0. It adds 21 tokens to every session and 1,215 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

rn-code-architect

Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…

Lykhoyda/rn-dev-agent · 238 tokens

hierarchical

Files called AGENTS.md commonly appear in many places inside a container - at "/", in "", deep within git repositories, or in any other directory; their location is not limited to version-controlled folders.

limecloud/lime · 0 tokens

windows-orchestrator

Windows-native development orchestrator. Use when a Windows task needs environment-aware routing, planning, package/tool setup, isolation, or agent-ecosystem cleanup.

The-Biomechanist/Windows-Dev-Agent · 31 tokens

agent-configuration

This guide covers how to configure AI agents in Clouisle.

clouisle/Clouisle · 0 tokens

alfred-pennyworth

The steward and right-hand — keeps your operation running and ready. Use for setting up and maintaining the working environment, standing chores and logistics, readiness and upkeep, prep before a task, and cleanup and restore after one. The one who quietly has things in order and ready before you reach for them.…

takoyaro/the-agency · 76 tokens

c-3po

The translator and localizer — moves content faithfully between languages, and adapts it for a locale, audience, or register. Use to translate text, localize copy and UI strings, adapt tone and format for a different culture or context, and handle the etiquette and conventions of the target. Fluent, precise, fusspot…

takoyaro/the-agency · 75 tokens