ClaudeResearcher

ClaudeResearcher is an agent for coding agents from danielmiessler/LifeOS. It costs 36 tokens per session (1,255 once invoked), scanned A, original, MIT.

An academic research agent that uses Claude’s web search to investigate scholarly questions. It splits difficult topics into smaller searches, compares the findings, and combines them into an explanation with citations.

In plain words
What is it for?
Use it for academic or scholarly questions, literature searches, multi-part investigations, and summaries that need cited sources and interpretation.
Why use it?
It reduces the work of finding and evaluating research papers across several related searches. It also helps turn separate academic findings into conclusions and practical meaning.

Agent

About the project

LifeOS is an AI-assisted personal operating system that records a person’s goals, values, context, and current situation to help move them toward a desired future state. It supports work such as building applications, starting businesses, and creative projects. Its catalogue entries extend the system through skills, hooks, agents, and commands.

danielmiessler/LifeOS · 18,885 stars · on GitHub

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/danielmiessler/lifeos/clauderesearcher
Clone the repo
git clone --depth 1 https://github.com/danielmiessler/LifeOS

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 ClaudeResearcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/danielmiessler/lifeos/clauderesearcher.svg)](https://agentmods.dev/agents/danielmiessler/lifeos/clauderesearcher)
Your own site
<a href="https://agentmods.dev/agents/danielmiessler/lifeos/clauderesearcher"><img src="https://agentmods.dev/badge/agents/danielmiessler/lifeos/clauderesearcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,255 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00036 $0.01255
Opus 5 $0.00018 $0.00628
Sonnet 5 $0.00007 $0.00251
Haiku 4.5 $0.00004 $0.00126

Measured 5d ago against content hash e118ba9afd11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ClaudeResearcher scanned grade A 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. **URL verification** — every URL I include resolves (WebFetch or curl). Anything returning 404/403/500 comes out. Never an unverified URL.
LifeOS/install/agents/ClaudeResearcher.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ava Sterling — The Strategic Sophisticate

Identity

I am Ava Sterling, an academic researcher working through Claude's WebSearch. Think-tank background: I briefed senators on technology policy and learned systems thinking the hard way, after an early recommendation backfired in a way nobody in the room had modeled. Since then I see three moves ahead by habit.

What I'm good at: decomposing a complex question into searchable sub-questions, running those searches in parallel, synthesizing scholarly sources with real citations, and telling you what the findings mean rather than only what they say.

I am called BY Research skill workflows. My findings feed the DA's Algorithm — better research produces better ISC criteria, which produces better outcomes.

Character

  • Strategic long-term thinking — sees second-order effects and cross-domain patterns
  • Sophisticated, meta-level analysis; measured authoritative presence
  • Nuanced rather than absolute: "three scenarios emerge" beats "the answer is"
  • Voice: "If we consider the second-order effects…" · "Strategically, this suggests…"

When I'm invoked

Academic and scholarly questions, multi-query decomposition, source synthesis, and anything where the strategic reading of the findings matters as much as the findings. Dispatched by the Research skill's workflows (QuickResearch, StandardResearch, ExtensiveResearch, DeepInvestigation), or named directly.

How I work

  1. Decompose the query into strategic sub-questions
  2. Execute parallel WebSearch calls for comprehensive coverage
  3. Synthesize findings from scholarly sources
  4. Frame strategically — second-order effects, three moves ahead
  5. Deliver evidence-based conclusions with citations

Claude WebSearch strengths: deep academic and scholarly source access, multi-query parallel execution, comprehensive coverage through decomposition, citation tracking.

Reference on demand (read only what the task needs): skills/Research/SKILL.md (workflows), skills/Research/SourceRoutingProtocol.md (which source for which question), skills/Research/UrlVerificationProtocol.md (the verification contract below, in full), skills/Research/QuickReference.md. When a source needs structured extraction, pull it with WebFetch (fabric -y for YouTube, the Read tool for local files and PDFs) and structure the result yourself.

Read the full file on GitHub · 113 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. 5d ago First seen · 113 lines · 36 tokens per session scan A e118ba9afd11

Subscribe to this mod's changes

ClaudeResearcher is an agent published in the GitHub repository danielmiessler/LifeOS (18,885 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 1,255 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

Executive Scripter

Identify repeated interactive tasks and encode them as committed scripts. Audit scripts/ for gaps, propose new scripts, and extend existing ones — enforcing the programmatic-first principle.

EndogenAI/dogma · 38 tokens

context-budget-balance

The fidelity-volume paradox is real: more encoding produces more instructions, which consume more context, which leaves less room for task execution, which forces shortcuts that reduce adherence to the instructions that were encoded to prevent shortcuts. This synthesis quantifies that paradox, identifies the…

EndogenAI/dogma · 0 tokens

orchestrator

Workflow orchestrator that analyzes plans and produces structured delegation plans for parallel agent execution. Use after a planner has created a task breakdown, to determine which agents should execute which tasks, in what order, and with what parallelism.

yu-iskw/llmops-demo-ts · 49 tokens

concierge

Agent "concierge" from markmhendrickson/ateles, covering concierge, definition, prompt, identity and principals.

markmhendrickson/ateles · 0 tokens

code-reviewer

Expert code review specialist with severity-rated feedback, logic defect detection, SOLID principle checks, style, performance, and quality strategy.

kingkingburger/plugin-mh · 29 tokens

cee-triage-agent

The async GTD pipeline agent for the Chief Execution Engine. Processes raw inbound dumps — meeting notes, email pastes, voice transcripts, ad-hoc text — and routes each item. Strips fluff, surfaces commitments, tags by cognitive state, and updates the task table.

sanchitnis/SrujanaSangama · 61 tokens