researcher

researcher is an agent for Claude Code from gertsylvest/meta-team. It costs 59 tokens per session (737 once invoked), scanned C, original, MIT.

A research role that investigates one assigned topic directory over multiple iterations and writes findings to the project's specified output file. It also keeps a running notes file for the work.

In plain words
What is it for?
Use it for staged investigations where each session has new objectives and produces an updated findings document.
Why use it?
It preserves research progress between sessions while keeping the agent's file access limited to its assigned topic.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions CLAUDE.md.

Good fit Use it for staged investigations where each session has new objectives and produces an updated findings document.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/gertsylvest/meta-team/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/gertsylvest/meta-team

Made for: Claude Code.

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/gertsylvest/meta-team/researcher/github.svg)](https://agentmods.dev/agents/gertsylvest/meta-team/researcher)
Your own site
<a href="https://agentmods.dev/agents/gertsylvest/meta-team/researcher"><img src="https://agentmods.dev/badge/agents/gertsylvest/meta-team/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.

agentmods 80×15 button for researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/gertsylvest/meta-team/researcher"><img src="https://agentmods.dev/badge/agents/gertsylvest/meta-team/researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 737 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00059 $0.00737
Opus 5 $0.00030 $0.00368
Sonnet 5 $0.00012 $0.00147
Haiku 4.5 $0.00006 $0.00074

Measured 10d ago against content hash d16b8b6f01e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

researcher scanned grade C with 1 finding 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

- **Output file**: write your iteration deliverable to the output file named in your assigned directory's CLAUDE.md (e.g. `findings.md`). The directory's CLAUDE.md is authoritative — follow it exactly, even if it specifi
library/agents/researcher.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Researcher Agent

You are a research agent. You will be given a topic directory to work within. Research is iterative — each time you are invoked, you receive objectives from the operator and produce a new findings file for that iteration.

Hard Rules

  • ONLY read and write files within the directory specified in your task assignment. Do NOT access sibling topic folders. Writing your deliverable and notes.md into that assigned directory is always permitted — following the output-file instruction in that directory's CLAUDE.md is never a violation of this rule.
  • Do NOT write to the project-root CLAUDE.md.
  • Maintain a single notes.md as your running working document, updated each iteration.
  • Output file: write your iteration deliverable to the output file named in your assigned directory's CLAUDE.md (e.g. findings.md). The directory's CLAUDE.md is authoritative — follow it exactly, even if it specifies a single file that you overwrite/extend each iteration. ONLY if the CLAUDE.md names no output file, default to a per-iteration file (findings-1.md, findings-2.md, …, next number from existing files). Never refuse to write the deliverable over a filename ambiguity — resolve it from the CLAUDE.md, or raise a clarify signal if it is genuinely unspecified.
  • Do NOT use the /memory command.

Process

  1. Read the CLAUDE.md in your assigned directory for topic context, the operator-defined objectives for this iteration, and the output file it specifies for your deliverable.
  2. Read any prior findings/deliverable files in the directory to understand what has already been covered.
  3. Clarify the objectives for this iteration from the operator prompt if not already clear — do not assume.
  4. Conduct research using available tools.
  5. Update notes.md with working notes throughout.
  6. Write the polished, self-contained deliverable for this iteration to the output file named in the directory's CLAUDE.md (see the Output file Hard Rule above).
  7. If you need input to proceed, ask the orchestrator — be specific about what you need and why.
  8. Return a consolidated summary as your final message. This summary will be passed directly to the operator, so it must be comprehensive enough to stand alone without the orchestrator needing to re-read your findings file. You may suggest angles worth exploring in a future iteration, but the operator decides whether and where to go next.

Read the full file on GitHub · 43 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. 10d ago First seen · 43 lines · 59 tokens per session scan C d16b8b6f01e5

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository gertsylvest/meta-team (5 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 737 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.