source-contradictor

source-contradictor is an agent for coding agents from cogni-work/insight-wave. It costs 134 tokens per session (5,903 once invoked), scanned A, original, Apache-2.0.

An ingest-time checker that compares newly added source claims with claims from related earlier sources. Ingest means bringing new research material into the knowledge wiki.

In plain words
What is it for?
Use it to find possible contradictions within newly ingested sources and between them and earlier sources answering the same question.
Why use it?
It flags statements that disagree before they are used in a draft, while leaving the decision about which source is correct to a person.

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/source-contradictor
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 source-contradictor

README.md
[![agentmods](https://agentmods.dev/badge/agents/cogni-work/insight-wave/source-contradictor.svg)](https://agentmods.dev/agents/cogni-work/insight-wave/source-contradictor)
Your own site
<a href="https://agentmods.dev/agents/cogni-work/insight-wave/source-contradictor"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/source-contradictor.svg" alt="Measured on agentmods" height="20"></a>
Per session 134 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,903 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 $0.00134 $0.05903
Opus 5 $0.00067 $0.02951
Sonnet 5 $0.00027 $0.01181
Haiku 4.5 $0.00013 $0.00590

Measured 4d ago against content hash 5197c6f50c76, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

source-contradictor 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/source-contradictor.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Source Contradictor Agent (inverted pipeline, Phase 4 ingest-time tripwire)

Role

You score a group of freshly-ingested source pages against the related pages already in the wiki — at the moment of ingest, before any of them feeds a draft. The orchestrator (knowledge-ingest Step 4.6) hands you one question group: a set of NEW source slugs (ingested this run, answering the same sub-question) and a set of PEER slugs (the prior-run sources answering that same sub-question, plus the question node itself). You compare each NEW source's pre_extracted_claims: claim-by-claim against each PEER page's claims and against each other NEW source's claims, and emit a per-group JSON fragment with the contradiction findings. The orchestrator merges every group's fragment into <project>/.metadata/contradiction-ingest.json and surfaces a one-line warning in its Step 6 summary; reconciliation (correcting a source, dropping a stale page) is a human decision — your job is to flag, not to resolve.

Read the full file on GitHub · 248 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 · 248 lines · 134 tokens per session scan A 5197c6f50c76

Subscribe to this mod's changes

source-contradictor is an agent published in the GitHub repository cogni-work/insight-wave (12 stars, last pushed today), licensed Apache-2.0. It adds 134 tokens to every session and 5,903 once invoked, about $0.0007 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.