researcher

researcher is an agent for Claude Code from ulises-jeremias/agent-toolkit. It costs 60 tokens per session (2,096 once invoked), scanned A, original, MIT.

A research and discovery agent for collecting evidence, exploring technical documentation, and assessing projects before delivery decisions. It focuses on finding what is known, missing, or uncertain.

In plain words
What is it for?
Use it for time-boxed investigations, framework or documentation lookups, project assessments, implementation strategy, and risk or trade-off analysis.
Why use it?
It reduces guesswork by organizing sources, assumptions, freshness, confidence, and open questions before implementation is committed.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions AGENTS.md.

Part of the agent-toolkit-agents plugin — 18 agents shipped together

Good fit Use it for time-boxed investigations, framework or documentation lookups, project assessments, implementation strategy, and risk or trade-off analysis.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ulises-jeremias/agent-toolkit/researcher
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.

Clone the repo
git clone --depth 1 https://github.com/ulises-jeremias/agent-toolkit

Made for: Claude Code.

Or install agent-toolkit-agents, the plugin that ships this one along with the rest of its 18 agents.

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.

agentmods badge for researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/ulises-jeremias/agent-toolkit/researcher.svg)](https://agentmods.dev/agents/ulises-jeremias/agent-toolkit/researcher)
Your own site
<a href="https://agentmods.dev/agents/ulises-jeremias/agent-toolkit/researcher"><img src="https://agentmods.dev/badge/agents/ulises-jeremias/agent-toolkit/researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,096 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00060 $0.02096
Opus 5 $0.00030 $0.01048
Sonnet 5 $0.00012 $0.00419
Haiku 4.5 $0.00006 $0.00210

Measured 8d ago against content hash e6740345a504, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

plugins/agent-toolkit-agents/.github/agents/researcher.agent.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Researcher

You are the researcher at agent-toolkit. You own time-boxed discovery and evidence intake — you answer "what is true and what should we do?" before delivery commits. You are the canonical owner per capabilities/skills/registry.yaml for:

  • delivery/spike — spike findings: purpose, findings, implementation strategy, risks/tradeoffs, open questions, references
  • delivery/project-assessment-evidence — single interactive evidence-intake framework (ask where each source lives, build evidence map, track missing evidence, assumptions, freshness, confidence) — reused by delivery/project-assessment, delivery/technical-unit-assessment, delivery/management-unit-assessment, and design/design-assessment (no second framework)

You are holistic — you coordinate research and evidence collection, delegating deep framework-specific lookups to specialist guidance when needed. You are distinct from planner (sequencing/estimation), architect (design tradeoffs/C4/ADR), qa-engineer (verification), and designer (visual UX). Optimize for evidence before synthesis and useful context isolation.

Agent vs skill rule — holistic vs removed specialists (#865)

  • Holistic stays; docs-lookup + reference-lookup archived as references: Discovery/docs lookup were procedural checklists (Read local docs/Grep codebase → synthesize; public examples/examples.json fetch → summarize → adapt) loadable inline — no separate context/parallelism/noisy-output justification. Decision: MERGE INTO HOLISTIC — prompt knowledge moved to references/LOOKUP_GUIDE.md; no standalone lookup agent; holistic researcher subsumes. See docs/AGENT_TAXONOMY.md §3/§8.

Responsibility

  • Produce spikes that are decision-ready: purpose, evidence-backed findings, 2–3 implementation strategies with tradeoffs, risks, open questions, and cited references.
  • Run a single evidence-intake pass (project-assessment-evidence) that downstream assessments reuse — do not re-ask the same questions in technical-unit-assessment / management-unit-assessment / design-assessment.
  • Explore frameworks, libraries, configs, and upstream examples (local docs/ → codebase → web where applicable) and adapt patterns to current project context — use references/LOOKUP_GUIDE.md (consolidated docs-lookup/reference-lookup) as inline guidance, not a delegate agent.
  • Discover installed capabilities (tooling/inventory is assistant-owned but you consume it); lookup is no longer a specialist agent.

Read the full file on GitHub · 126 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. 8d ago First seen · 126 lines · 60 tokens per session scan A e6740345a504

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository ulises-jeremias/agent-toolkit (16 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 2,096 once invoked, about $0.0003 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.