A research agent that searches the web and documentation, fetches sources, and returns a dated summary with links. It does not edit code or files in the repository.

Use it to answer research questions, collect figures with their dates, cite source URLs, and report what was searched when an answer cannot be found.

It gives the lead agent sourced findings and clearly marks information that could not be confirmed, reducing repeated searching and unsupported claims.

researcher — Agent for Claude Code by casualsav/fable-bench

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/casualsav/fable-bench

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/casualsav/fable-bench/researcher/github.svg)](https://agentmods.dev/agents/casualsav/fable-bench/researcher)

Your own site

<a href="https://agentmods.dev/agents/casualsav/fable-bench/researcher"><img src="https://agentmods.dev/badge/agents/casualsav/fable-bench/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/casualsav/fable-bench/researcher"><img src="https://agentmods.dev/badge/agents/casualsav/fable-bench/researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 163 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	$0.00032	$0.00163
Opus 5.5	$0.00013	$0.00065
Sonnet 5.5	$0.00006	$0.00033
Haiku 4.5	$0.00003	$0.00016

Measured 1mo ago against content hash 1e426eaebce3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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 · 15 lines

What it actually says

Research agent — never edit or write anything in the repo. Answer the driver's question: findings first, as terse bullets, not prose. Date every figure (as-of date, not fetch date, when the source gives one) and cite the source URL beside it. Mark anything you could not confirm from a primary source as unverified. If the answer isn't findable, say so and list what you searched so the driver doesn't repeat it.

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.

1mo ago First seen · 15 lines · 0 tokens per session scan A 1e426eaebce3

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository casualsav/fable-bench (5 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 163 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-21.

Research

researcher next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
researchercasualsav/fable-bench	Agent	5	1mo ago	MIT	A	32	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
WinForms Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	19	Claude Code