# fact-checker

A Claude subagent that pulls verifiable claims out of a text and rates how trustworthy the sources behind them are. Handy before you publish a draft or repeat someone's number.

- subagent · `type=agent` · Claude Code · 1919 installs
- Author: davila7
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/agents/deep-research-team/fact-checker.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/agents/fact-checker

## What it does

The subagent extracts specific claims: statistics, attributions, causal statements. Then it looks for supporting and contradicting evidence, compares them, and assigns a status from TRUE down to UNVERIFIABLE. Source credibility gets its own pass — domain type, methodology, signs of bias.

Under the hood is a Python engine class. It matches numeric claims by pattern, collects sources on both sides, and computes a confidence score between 0.0 and 1.0. WebSearch and WebFetch handle the lookups and page fetches; Read, Write and Edit cover files.

The source text is cut off, so the full verification routine isn't visible from it. No web access means no evidence gathering — worth checking your web tools are enabled before you rely on it.

## Install

### Claude Code (native platform)

1. **claude-code-templates**
```bash
npx claude-code-templates@latest --agent deep-research-team/fact-checker
```

2. **Manually: put the files in place**
- File: `.claude/agents/fact-checker.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/fact-checker.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/fact-checker.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/agents/deep-research-team/fact-checker.md

## When to use it
- break a draft into claims that can actually be checked
- judge whether a given site or article deserves trust
- trace a statistic back to its original source
- catch a false claim before the piece goes out
- verify a quote and who it is attributed to

## Example prompts
- fact-check this draft and flag the claims that don't hold up
- assess how credible this source is
- find the original source for this statistic

## Similar
- [Doublecheck](https://affpapa.org/en/nevibecode/agents/doublecheck.md) — subagent · ★ 40418
- [frontend-developer](https://affpapa.org/en/nevibecode/agents/voltagent-community-frontend-developer.md) — subagent · 40905 installs
- [dx-optimizer](https://affpapa.org/en/nevibecode/agents/dx-optimizer.md) — subagent · 1198 installs
- [mlops-engineer](https://affpapa.org/en/nevibecode/agents/voltagent-community-mlops-engineer.md) — subagent · 1009 installs
- [postgres-pro](https://affpapa.org/en/nevibecode/agents/postgres-pro.md) — subagent · 897 installs
- [agent-installer](https://affpapa.org/en/nevibecode/agents/agent-installer.md) — subagent · 363 installs
- [embedded-systems](https://affpapa.org/en/nevibecode/agents/embedded-systems.md) — subagent · 279 installs

From the same set: [davila7/claude-code-templates](https://affpapa.org/en/nevibecode/by/davila7/claude-code-templates.md) — 205 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
