No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by SerhiiKorniienko · Agent Tool · ★ 139
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is bullshit-detector safe to install? View the security audit →
Bullshit Detector Agent skills that fact-check the internet. Point your agent at a viral YouTube video, article, tweet, or PDF — get a claim-by-claim verification report with sources and a BS score (0–10) instead of taking "10 WAYS TO MAKE MONEY WITH AI 🤯" at face value. Portable Agent Skills — plain markdown + self-contained Python. They work in Claude Code, Codex, OpenCode, and any harness that supports the skills format and has web search. Built in the open with Claude Code — an AI helped build the tool that fact-checks AI hype, and the example report is it auditing its own kind. Follow @SerhiiFounder for new skills and fact-check experiments, or join the newsletter to get them in your inbox. Quickstart Install uv if you don't have it (the fetch script uses it to self-resolve its dependencies). Run the skills.sh installer and pick the skills and agents you want: Ask your agent: "is this bullshit? \", "fact-check this video", "summarize \", "explain the part at 12:30". Install as a Claude Code plugin Prefer a managed bundl
| Stars | 139 |
| Forks | 9 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 72.2704922380716/100 |
| Open Issues | 5 |
| Last Updated | 2026-09-03 |
| Created | 2026-07-27 |
| Platforms | claude-code, python |
| Est. Tokens | ~16k |
These tools work well together with bullshit-detector for enhanced workflows:
Looking for a bullshit-detector alternative? If you're comparing bullshit-detector with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
One-stop shop for AI skills and agents. Search 110K+ community skills, install and track them declaratively, a
Claude Code skills for journalism, media, and academia - verification, FOIA, data journalism, academic writing
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
Portable SKILLs workspace for Claude Code, Codex, and Gemini — issue-driven workflows and cross-agent collabor
Cognitive Deterministic Memory Security OS for Agentic AI. Deterministic root-cause retrieval that reaches bac
OpenClaw-inspired autonomous AI agent built entirely in n8n. Adaptive RAG-powered memory, Skills via MCP templ
Explore other popular agent tool tools:
bullshit-detector is Agent skills that fact-check the internet: claim-by-claim verification with sources and a 0-10 BS score for any YouTube video, article, tweet, or PDF. It is categorized as a Agent Tool with 139 GitHub stars.
bullshit-detector is primarily written in Python. It covers topics such as agent-skills, ai-agents, claude-code.
You can find installation instructions and usage details in the bullshit-detector GitHub repository at github.com/SerhiiKorniienko/bullshit-detector. The project has 139 stars and 9 forks, indicating an active community.
bullshit-detector is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to bullshit-detector on Agent Skills Hub include skillfile, claude-skills-journalism, claudepro-directory. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: