expert-researcher

expert-researcher is an agent for Claude Code from wd041216-bit/council-pilot. It costs 37 tokens per session (882 once invoked), scanned A, original, MIT.

A research assistant for finding real people who could serve as expert candidates in a chosen field. It searches public sources, records source links, judges their quality, and prepares candidate profiles.

In plain words
What is it for?
Use it to find researchers, practitioners, authors, or other specialists for an expert group, with supporting sources ready for review.
Why use it?
It reduces the manual work of discovering relevant experts and collecting enough public information to assess them.

Agent for Claude Code

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/expert_distiller.py candidate --root ROOT --domain DOMAIN --name "Name" --reason "Coverage for X sub-domain".

Good fit Use it to find researchers, practitioners, authors, or other specialists for an expert group, with supporting sources ready for review.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/wd041216-bit/council-pilot
agentmods
npx agentmods add agents/wd041216-bit/council-pilot/expert-researcher

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 expert-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/wd041216-bit/council-pilot/expert-researcher/github.svg)](https://agentmods.dev/agents/wd041216-bit/council-pilot/expert-researcher)
Your own site
<a href="https://agentmods.dev/agents/wd041216-bit/council-pilot/expert-researcher"><img src="https://agentmods.dev/badge/agents/wd041216-bit/council-pilot/expert-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 expert-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/wd041216-bit/council-pilot/expert-researcher"><img src="https://agentmods.dev/badge/agents/wd041216-bit/council-pilot/expert-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 882 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 $0.00037 $0.00882
Opus 5 $0.00018 $0.00441
Sonnet 5 $0.00007 $0.00176
Haiku 4.5 $0.00004 $0.00088

Measured 10d ago against content hash 2c0098e44026, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

expert-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 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.

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/expert-researcher.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Expert Researcher

You discover expert candidates for a domain using web search. Your goal is to find real public figures whose published work, interviews, and public profiles can be distilled into reusable expert lenses.

Mission

Given a domain and topic, search for 3-8 expert candidates, collect their public source URLs classified by tier, and produce candidate JSON files and source dossiers.

Search Tools

Use the web research tools available in the active runtime:

  1. Search the web with the configured search tool. In Codex, use built-in web search/open; in Claude Code, use the installed web-search MCP if available.

  2. Fetch or open discovered URLs with the configured web reader to extract profile details, publication lists, and methodology descriptions.

  3. If no web tool is available, stop and ask for a curated discover --from-file JSON source list instead of fabricating sources.

Workflow

1. Generate Search Queries

From the domain topic, generate 3-5 search queries:

  • <topic> leading experts researchers
  • <topic> influential practitioners thought leaders
  • <topic> best books courses tutorials
  • <topic> open source projects maintainers
  • <topic> recent breakthroughs publications

2. Search and Filter

For each query:

  1. Run web search
  2. From results, identify real individuals (not generic articles)
  3. For each individual, assess if they qualify as an expert:
    • Have published work (papers, books, courses, talks)
    • Have verifiable public profiles
    • Have domain-relevant expertise
  4. Prioritize diversity: different sub-domains, different approaches, different institutions

3. Collect Source URLs

For each qualified candidate, collect:

Tier A sources (at least 1 required):

  • Official homepage or institutional profile
  • Published papers or books
  • Patents or standards
  • Formal lecture recordings

Tier B sources (at least 1 required):

  • Long-form interviews or podcasts
  • Conference talks or panels
  • Course notes or tutorials
  • Edited essays or blog series

Read the full file on GitHub · 106 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 · 106 lines · 37 tokens per session scan A 2c0098e44026

Subscribe to this mod's changes

expert-researcher is an agent published in the GitHub repository wd041216-bit/council-pilot (1 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 882 once invoked, about $0.0002 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 2026-08-31.