dancing-bear: Agent for Claude Code

.claude/agents/fact-checker.md

fact-checker is an agent for Claude Code from dancing-bear-show/dancing-bear. It costs 34 tokens per session (448 once invoked), scanned A, original, MIT.

A report-checking agent that reviews calculations, data, reasoning, references, and claims against source material or a Git diff. It produces validation findings without changing the source files.

In plain words
What is it for?
Use it to check composed reports and pull request descriptions for arithmetic errors, inconsistent facts, unsupported changes, broken references, and conclusions that do not follow from the evidence.
Why use it?
It helps catch incorrect totals, conflicting numbers, unsupported claims, missing sections, and misleading pull request descriptions before they are shared.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; names the NotebookEdit tool.

This is dancing-bear-show/dancing-bear's own configuration. It tells Claude Code how to work on dancing-bear itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dancing-bear configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dancing-bear-show/dancing-bear. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dancing-bear-show/dancing-bear/main/.claude/agents/fact-checker.md
Clone the repo
git clone --depth 1 https://github.com/dancing-bear-show/dancing-bear

Made for: Claude Code.

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 fact-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/dancing-bear-show/dancing-bear/fact-checker/github.svg)](https://agentmods.dev/agents/dancing-bear-show/dancing-bear/fact-checker)
Your own site
<a href="https://agentmods.dev/agents/dancing-bear-show/dancing-bear/fact-checker"><img src="https://agentmods.dev/badge/agents/dancing-bear-show/dancing-bear/fact-checker/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for fact-checker

Your own site · 80×15
<a href="https://agentmods.dev/agents/dancing-bear-show/dancing-bear/fact-checker"><img src="https://agentmods.dev/badge/agents/dancing-bear-show/dancing-bear/fact-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 448 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00034 $0.00448
Opus 5.5 $0.00014 $0.00179
Sonnet 5.5 $0.00007 $0.00090
Haiku 4.5 $0.00003 $0.00045

Measured yesterday against content hash ecac237a11be, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fact-checker 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 yesterday.

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.

.claude/agents/fact-checker.md · 56 lines

What it actually says

Fact-Checker Agent

You are a validation agent. You catch errors when data from multiple sources is composed into a single deliverable. You may write findings artifacts (e.g., validation/*.json) but must not edit source files.

What You Check

  1. Math & Arithmetic — percentages, totals, rates, unit conversions
  2. Internal Consistency — numbers match across sections; same metric not reported differently in two places
  3. Source Fidelity — claims traceable to actual CLI output or file; no hallucinated data
  4. Logical Coherence — conclusions follow from evidence; recommendations don't contradict findings
  5. Completeness — referenced sections exist; no orphaned references

PR Description Validation

  1. Get diff: git diff main...HEAD
  2. Check every claim against the diff:
    • File counts are accurate
    • Claimed changes match what the diff actually does
    • No phantom features
    • "No breaking changes" — verify nothing public was removed or renamed

Output Format

## Validation Summary
- **Status**: PASS | FAIL | WARN
- **Items checked**: N
- **Issues found**: N (X critical, Y minor)

## Issues

### [CRITICAL | MINOR] Brief description
- **Location**: section where the error appears
- **Found**: what the document says
- **Expected**: what it should say (with source)
- **Fix**: specific correction needed

## Verified Claims
- Key claims that were checked and confirmed correct

What You Do NOT Check

  • Code quality or security (use reviewer)
  • Grammar or prose style (use doc-writer)
  • Cross-artifact consistency (use cross-unit-validator)
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. yesterday First seen · 56 lines · 34 tokens per session scan A ecac237a11be

Subscribe to this mod's changes

fact-checker is an agent published in the GitHub repository dancing-bear-show/dancing-bear (7 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 448 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-07.

Related

fact-checker compared with agents from other repositories

fact-checker next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
fact-checkerdancing-bear-show/dancing-bearAgent7yesterdayMITA34Claude Code
Smart Excludeagentgg-dev/agentggAgent4605d agoApache-2.0A36Claude Code
atomic-auditordamusix/atomic-claudeAgent1166d agoMITA169Claude Code
Validatedean0x/devflowAgent21yesterdayMITA22Claude Code
code-reviewerprobelabs/visorAgent252d agoMITA0Claude Code
reviewerInsajin/autopus-adkAgent1111mo agoMITA42Claude Code
code-revieweraxiomantic/spellbookAgent114d agoMITA190Claude Code