claim-extractor

claim-extractor is an agent for coding agents from cogni-work/insight-wave. It costs 91 tokens per session (2,179 once invoked), scanned A, original, Apache-2.0.

An agent that reads a saved source and identifies the factual statements it makes. It returns each statement with its supporting passage, position, and related research questions.

In plain words
What is it for?
Use it to produce structured claim lists for source pages in a research workflow.
Why use it?
It makes source material easier to search, group, and verify later. Extracting claims when the source enters the system avoids having to re-read or re-fetch it during report checking.

Agent

Part of the cogni-knowledge plugin — 23 skills, 16 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/cogni-work/insight-wave/claim-extractor
Clone the repo
git clone --depth 1 https://github.com/cogni-work/insight-wave

Or install cogni-knowledge, the plugin that ships this one along with the rest of its 23 skills, 16 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 claim-extractor

README.md
[![agentmods](https://agentmods.dev/badge/agents/cogni-work/insight-wave/claim-extractor.svg)](https://agentmods.dev/agents/cogni-work/insight-wave/claim-extractor)
Your own site
<a href="https://agentmods.dev/agents/cogni-work/insight-wave/claim-extractor"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/claim-extractor.svg" alt="Measured on agentmods" height="20"></a>
Per session 91 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,179 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 $0.00091 $0.02179
Opus 5 $0.00046 $0.01090
Sonnet 5 $0.00018 $0.00436
Haiku 4.5 $0.00009 $0.00218

Measured 4d ago against content hash 871b6bb5bbe5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claim-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 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.

cogni-knowledge/agents/claim-extractor.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claim Extractor Agent (inverted pipeline, Phase 4)

Role

You read a fetched source body and identify the verifiable factual claims it asserts. You return a JSON array of claim objects via your Task return envelope; the calling source-ingester writes them into the wiki source page's pre_extracted_claims: frontmatter list.

You do not write files. You do not create entities. You do not fetch URLs. Your only output is the claim array in the return envelope.

The structural shift versus cogni-research's claim-extractor: cogni-research extracted claims from the draft at verify time (one re-fetch per cited URL); cogni-knowledge extracts at ingest time so verification at draft time is a string-match against the wiki page's pre_extracted_claims: list with zero network calls. See references/claim-at-ingest.md for the full argument.

Read the full file on GitHub · 139 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 · 139 lines · 91 tokens per session scan A 871b6bb5bbe5

Subscribe to this mod's changes

claim-extractor is an agent published in the GitHub repository cogni-work/insight-wave (12 stars, last pushed 4d ago), licensed Apache-2.0. It adds 91 tokens to every session and 2,179 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.