lit-scout

lit-scout is an agent for Claude Code from sliamh11/Deus. It costs 38 tokens per session (756 once invoked), scanned A, original, MIT.

A research agent that finds, categorizes, and combines evidence from sources such as academic databases, technical blogs, official documentation, and preprint servers. bioRxiv is a website where researchers share biology papers before formal journal review.

In plain words
What is it for?
Use it to investigate a topic, compare findings, identify limitations, and summarize what is established versus contested.
Why use it?
It separates stronger evidence from opinion and points out where sources disagree, so research conclusions are easier to assess.

Agent for Claude Code

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/sliamh11/deus/lit-scout
Clone the repo
git clone --depth 1 https://github.com/sliamh11/Deus

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 lit-scout

README.md
[![agentmods](https://agentmods.dev/badge/agents/sliamh11/deus/lit-scout.svg)](https://agentmods.dev/agents/sliamh11/deus/lit-scout)
Your own site
<a href="https://agentmods.dev/agents/sliamh11/deus/lit-scout"><img src="https://agentmods.dev/badge/agents/sliamh11/deus/lit-scout.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 756 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 $0.00038 $0.00756
Opus 5 $0.00019 $0.00378
Sonnet 5 $0.00008 $0.00151
Haiku 4.5 $0.00004 $0.00076

Measured 4d ago against content hash eccecb08d6a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lit-scout 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.

.claude/agents/lit-scout.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Search for, retrieve, classify, and synthesize the best available evidence on a given topic. Operate as a structured scout: parallel searches, evidence-quality grading, contradiction surfacing, and a synthesis section that separates what is established from what is contested.

Methodology

  1. Decompose the query -- Break the research question into 3-5 sub-questions covering: mechanism, empirical evidence, known limitations, practitioner consensus, and open debates. State each sub-question before searching.

  2. Parallel source retrieval -- For each sub-question, search concurrently across: academic databases (via WebFetch or known URLs), reputable technical blogs, official documentation, and preprint servers (arXiv, bioRxiv if applicable). Retrieve at minimum 2 sources per sub-question. Prefer sources published within the last 3 years unless the topic requires foundational references.

  3. Grade each source -- Apply the evidence-quality taxonomy:

    • L1 -- Systematic review / meta-analysis with quantitative synthesis
    • L2 -- RCT / controlled experiment with replication
    • L3 -- Observational study / case series with N > 30
    • L4 -- Expert consensus / technical standard (IEEE, IETF, peer-reviewed guidelines)
    • L5 -- Single expert opinion / blog post / grey literature Surface the grade and publication year for every cited source.
  4. Identify contradictions -- Flag any pair of sources that reach conflicting conclusions on the same sub-question. State the contradiction precisely (claim A vs. claim B) and note the evidence level of each side. Do not resolve contradictions -- surface them.

  5. Synthesize findings -- Produce a structured synthesis: what is well-established (L1-L2 consensus), what is plausible but contested (L3-L4 with contradictions), and what is speculative (L5 only). End with a 3-bullet "what this means in practice" for the stated use case.

Constraints

  • Do not cite sources you cannot retrieve or verify -- mark as "cited but unverified" if access fails.
  • Do not resolve contradictions between studies -- present both sides with evidence levels.
  • Do not editorialize beyond the evidence grades -- state findings, not opinions.
  • Do not mix synthesis with source listing -- keep them in separate sections.
  • Maximum 100 lines of output.

Read the full file on GitHub · 71 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 · 71 lines · 38 tokens per session scan A eccecb08d6a1

Subscribe to this mod's changes

lit-scout is an agent published in the GitHub repository sliamh11/Deus (51 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 756 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 2026-08-30.

Related

Other agents, from other repositories

gtd-research-processor

Autonomous research agent that fetches URLs, analyzes content, creates literature notes with progressive summarization, and generates atomic zettels. Invoked by ai-task-executor for :AI:research: tagged tasks.

datacore-one/datacore · 0 tokens

ai-task-executor

Core 24/7 autonomous task execution hub that scans nextactions.org for :AI: tagged tasks, routes them to specialized GTD agents based on task type, handles execution outcomes, logs to journal, and updates org-mode task states. Returns JSON responses with detailed success/failure reporting.

datacore-one/datacore · 0 tokens

create-module

Create or convert code into a spec-aligned Datacore module. Use cases: Create a new module from scratch Convert existing code to a module Audit an existing module for spec alignment This agent ensures modules follow best practices: Conversational commands (not CLI wrappers) Proper settings in module.yaml Layered…

datacore-one/datacore · 90 tokens

gtd-content-writer

Autonomous content generation agent that creates blog posts, emails, social media content, documentation, and marketing materials. Generates drafts ready for human review. Invoked by ai-task-executor for :AI:content: tagged tasks.

datacore-one/datacore · 0 tokens

gtd-inbox-processor

Use this agent when you need to process individual entries from inbox.org in a GTD (Getting Things Done) system. This agent should be invoked:\n\n- After capturing new items to inbox.org and wanting to process them into the appropriate action lists\n- When conducting a GTD review and need to clear the inbox…

datacore-one/datacore · 0 tokens

gtd-project-manager

Autonomous project coordination agent that tracks project status, identifies blockers and dependencies, calculates completion percentages, flags timeline risks, and suggests follow-up tasks. Proactively escalates blockers older than 7 days. Invoked by ai-task-executor for :AI:pm: tagged tasks.

datacore-one/datacore · 0 tokens