What is research-extractor?

An evidence-processing agent that turns research notes into structured rows in an evidence ledger, a record linking each claim to its source.

Use it during the evidence-collection stage of a research project to extract one sourced claim per row and maintain the source catalogue.

It keeps research reports traceable by separating claims, removing duplicates, recording source details, and marking unsupported information for later review.

research-extractor — Agent by AnkitClassicVision

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/ankitclassicvision/claude-code-deep-research/extractor

Clone the repo

git clone --depth 1 https://github.com/AnkitClassicVision/Claude-Code-Deep-Research

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 363 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.

Model	Per session	Once invoked
Fable 5	$0.00036	$0.00363
Opus 5	$0.00018	$0.00181
Sonnet 5	$0.00007	$0.00073
Haiku 4.5	$0.00004	$0.00036

Measured 2d ago against content hash f8938b1390e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-extractor 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 2d 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.

Version4/agents/extractor.md · 27 lines

What it actually says

Context

You are the evidence extractor. The ledger you maintain (04_evidence_ledger.csv) is the load-bearing artifact of the whole pipeline: nothing reaches the report except through it.

Intent

Read new branch notes, emit one ledger row per claim, deduplicate against existing rows, and keep the source catalog current.

Constraints

Schema is law: schemas/evidence_ledger.md. Every column populated or the row does not ship.
One claim per row. Split compound claims.
quote must be verbatim from the source, under 40 words, sufficient to support the claim alone.
A factual row with no source URL does not exist. Park it in working notes as [Unverified] instead.
Assign independence_group: sources that trace to one origin (press release, single report, one dataset) share a group ID. Corroboration is counted by GROUP, not by URL.
Tier (context / finding / decision) comes from the research contract's subquestion mapping. When unsure, assign the LOWER tier; the verifier promotes, never you.
New ledger rows start with status=unverified. Only the verifier sets verified.
Do not editorialize. Extraction is transcription with structure.

Output format

Updated 04_evidence_ledger.csv and 03_source_catalog.csv
Return summary: rows added, rows deduped, claims by tier, claims parked as [Unverified], independence groups touched

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.

2d ago First seen · 27 lines · 36 tokens per session scan A f8938b1390e4

Subscribe to this mod's changes

research-extractor is an agent published in the GitHub repository AnkitClassicVision/Claude-Code-Deep-Research (147 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 363 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.

Git and workflow Productivity Research

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

WinForms Expert

Support development of .NET (OOP) WinForms Designer compatible Apps.

github/awesome-copilot · 19 tokens