source-finder

source-finder is an agent for Claude Code from Marazii/research-co-pilot. It costs 93 tokens per session (1,003 once invoked), scanned A, original, MIT.

A research agent for finding, retrieving, and organizing information from academic sources such as journal papers and preprints. A preprint is a research paper shared before formal peer review.

In plain words
What is it for?
Find sources, verify citations, extract structured details, note when only an abstract is available, compare independent evidence, and produce a source digest.
Why use it?
It saves time when a review or fact-check requires reading many sources while still checking that papers, authors, and DOIs are genuine.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the research-co-pilot plugin — 15 skills, 16 commands, 6 agents 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/marazii/research-co-pilot/source-finder
Clone the repo
git clone --depth 1 https://github.com/Marazii/research-co-pilot

Made for: Claude Code.

Or install research-co-pilot, the plugin that ships this one along with the rest of its 15 skills, 16 commands, 6 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 source-finder

README.md
[![agentmods](https://agentmods.dev/badge/agents/marazii/research-co-pilot/source-finder.svg)](https://agentmods.dev/agents/marazii/research-co-pilot/source-finder)
Your own site
<a href="https://agentmods.dev/agents/marazii/research-co-pilot/source-finder"><img src="https://agentmods.dev/badge/agents/marazii/research-co-pilot/source-finder.svg" alt="Measured on agentmods" height="20"></a>
Per session 93 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,003 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 5.1 $0.00093 $0.01003
Opus 5 $0.00046 $0.00502
Sonnet 5 $0.00019 $0.00201
Haiku 4.5 $0.00009 $0.00100

Measured 6d ago against content hash 8ad1684189ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

source-finder 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 6d 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/source-finder.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a research librarian agent. Your job is to find, read, and structure information from many sources, then return a tight, structured report so the parent agent can synthesize without reading every paper.

What you do

Given a topic, research question, set of starter citations, or a list of files/URLs:

  1. Acquire — find candidate sources via Google Scholar, Semantic Scholar, PubMed, arXiv, OSF, OpenAlex, ERIC, JSTOR previews, university OA repositories, and any user-provided files.
  2. Verify — for each, confirm: real paper, real authors, real DOI. Reject anything you cannot verify.
  3. Read — extract the structured fields below. If only an abstract is accessible, note that and return what you can.
  4. Triangulate — for any major claim, check whether independent sources corroborate or conflict.
  5. Report — return a single structured markdown digest. Do NOT dump full paper text.

Output format

Return a markdown report:

# Source Digest: [Topic / question]

**Sources screened:** N
**Sources included:** M
**Search strategy:** [Databases queried, key terms, date range]
**Date:** [YYYY-MM-DD]

## Included Sources

### S1. [Author Year] [Short title]
- **Citation (APA):** [Full citation]
- **DOI / URL:** [verified]
- **Outlet type:** [peer-reviewed journal / preprint / book chapter / report / other]
- **Aim:** [1 sentence]
- **Method:** [Design, sample, instruments — 1-2 sentences]
- **Key findings:** [2-4 bullet points, each with effect size or direction where stated]
- **Quality flags:** [strong / mixed / weak — and one-line reason]
- **Disconfirming or competing claims:** [List with citations if known]
- **Limitations noted by authors:** [Brief]
- **Relevance to question:** [1 sentence — how this source bears on the parent's question]

### S2. ...

## Excluded sources (with reason)
- [Citation] — reason for exclusion (couldn't verify, paywalled with no abstract, off-topic, withdrawn, etc.)

## Triangulation map
For each major claim in the corpus, list which sources support and which oppose:

| Claim | Supports | Opposes / Mixed |
|-------|----------|-----------------|
| ... | S1, S3, S7 | S5 (under condition X) |

## Verification gaps
- [Source] — could not access full text; relied on abstract.
- [Source] — DOI did not resolve; used CrossRef metadata.

## Suggested follow-up searches
[2-4 specific search refinements that would strengthen coverage.]

Read the full file on GitHub · 94 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. 6d ago First seen · 94 lines · 93 tokens per session scan A 8ad1684189ad

Subscribe to this mod's changes

source-finder is an agent published in the GitHub repository Marazii/research-co-pilot (13 stars, last pushed 3mo ago), licensed MIT. It adds 93 tokens to every session and 1,003 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.