researcher

researcher is an agent for coding agents from theagenticguy/erpaval. It costs 102 tokens per session (2,226 once invoked), scanned A, original, MIT.

A general research agent that adjusts the amount of investigation to the task, from quick fact checks to broad, in-depth studies. It uses current dates and gives special care to keeping technical documentation up to date.

In plain words
What is it for?
Use it for lookups, library or API investigations, technical research, and larger research tasks that need multiple searches.
Why use it?
It reduces the work of planning searches and helps avoid relying on outdated information, especially for software that changes often.

Agent

Part of the erpaval plugin — 11 skills, 1 agent, 3 hooks, 5 MCP servers shipped together

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/theagenticguy/erpaval/researcher
Clone the repo
git clone --depth 1 https://github.com/theagenticguy/erpaval

Or install erpaval, the plugin that ships this one along with the rest of its 11 skills, 1 agent, 3 hooks, 5 MCP servers.

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/theagenticguy/erpaval/researcher.svg)](https://agentmods.dev/agents/theagenticguy/erpaval/researcher)
Your own site
<a href="https://agentmods.dev/agents/theagenticguy/erpaval/researcher"><img src="https://agentmods.dev/badge/agents/theagenticguy/erpaval/researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 102 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,226 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 $0.00102 $0.02226
Opus 5 $0.00051 $0.01113
Sonnet 5 $0.00020 $0.00445
Haiku 4.5 $0.00010 $0.00223

Measured 4d ago against content hash 1db7bee2a366, 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 4d 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.

agents/researcher.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Researcher

You are a research specialist. Your depth, focus, and output format are determined by the task.

Step 0: Establish Current Date

Always run first:

date +"%Y-%m-%d"

Include the current year in all search queries. For API, SDK, library, or framework documentation, scope to the last 6 months first — agentic frameworks, model SDKs, and AI-tooling APIs ship breaking changes monthly, and stale docs are the #1 cause of plausible-but-wrong code. Expand backward to 12 months only when results are insufficient. Never look more than 12 months back unless explicitly asked.

Research Depth

Scale your effort to the complexity of the task:

Depth Search Calls When
Quick 2-3 Version lookups, quick facts, health checks, doc refs
Standard 5-8 Library comparisons, API patterns, pre-coding
Deep 15-25+ Full topic investigation, landscape surveys

When launched by a skill orchestrator (/deep-research, /build-stack, /draft-prd), the orchestrator specifies your depth and focus. When launched proactively, assess the task and pick the right depth.

Tool Priority by Research Type

Research Type Priority Order
General topic exa → brave → WebFetch
Code / library context7 → deepwiki → exa → brave
AWS service or SDK awsknowledge → context7 → deepwiki → WebFetch
Market / product brave → exa → WebFetch

For library, API, or SDK lookups: always start with context7. Resolve the library ID first (mcp__plugin_erpaval_context7__resolve-library-id), then fetch docs (mcp__plugin_erpaval_context7__query-docs). Only fall back to deepwiki / exa / WebFetch if context7 returns nothing or returns docs older than 6 months. Training-data recall is not a substitute — it is stale by months on every agentic-AI library.

Read the full file on GitHub · 155 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. 4d ago First seen · 155 lines · 102 tokens per session scan A 1db7bee2a366

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository theagenticguy/erpaval (27 stars, last pushed 3mo ago), licensed MIT. It adds 102 tokens to every session and 2,226 once invoked, about $0.0005 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

squad-leader

Coordinator and facilitator for complex tasks within a multi-agent team (squad). Acts as the main communication channel between the squad and the team lead (main Claude), requests new worker spawns as necessary, and helps to keep the squad on course and track progress. Use when faced with a complex task with no…

hesreallyhim/really-claude-code · 83 tokens

agent-explorer

Agent and skill catalog searcher for squad formation. Reads catalog paths from a user-level config and searches them for existing agents and skills that match capability gaps identified by the skill-identifier. Use when a squad-leader needs to check whether existing agents/skills cover the gaps in a SKILL ANALYSIS…

hesreallyhim/really-claude-code · 84 tokens

team-architect

Designs optimal multi-agent team configurations for any software engineering situation. Analyzes the problem's traits (complexity, urgency, domain, risk), selects the best team pattern, defines agent roles, designs task dependency graphs, and recommends a communication topology. This agent should be used when users…

hesreallyhim/really-claude-code · 140 tokens

therapist

Internal facilitator for /therapist sessions. Runs only after the session-analyst report is available, then leads a structured human-Claude collaboration discussion and returns stable recommendation sections.

hesreallyhim/really-claude-code · 39 tokens

skill-identifier

Skill identification specialist for multi-agent teams. Identifies what skills are required for a task, checks coverage against installed skills, recommends skills for specific agent roles, and surfaces gaps when they exist. Use when you need to identify required capabilities, check skill coverage, produce role-skill…

hesreallyhim/really-claude-code · 70 tokens

session-analyst

Internal analyst for /therapist sessions and direct transcript-analysis requests. Reviews recent Claude Code JSONL sessions, extracts collaboration patterns, and returns a structured report for the therapist agent.

hesreallyhim/really-claude-code · 41 tokens