Is the Anti-Hallucination skill free?

Yes. The skill itself is free from a-ariff/ariff-claude-plugins. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Anti-Hallucination SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 4/5.

How do I install Anti-Hallucination?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Anti-Hallucination with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Anti-Hallucination

A verification-hierarchy checklist that catches guessed facts before they're stated.

by a-ariff · a-ariff/ariff-claude-plugins

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 15, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 6fc5fc7

Concrete A/B: asked an unverified guess about a CLI's flag-combination behavior vs. actually reading the 228-line script -- the guess ('probably ignores --title') was wrong, the file shows it throws a hard usage error (exit 2) when --validate is combined with --title/--out-dir/--mode/--input; the skill's own discipline is what catches that gap.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 4/5

What Anti-Hallucination does

Anti-Hallucination is a pure prompting methodology (no scripts, no external files) that ranks claims by evidence strength -- direct file read, search result, inference, general knowledge, or unverified guess -- and requires Claude to say 'I don't know, let me check' rather than assert unverified specifics. It triggers whenever accuracy matters: verifying file contents, function signatures, dependency versions, or any claim about a specific codebase before stating it as fact.

How to install Anti-Hallucination

git clone https://github.com/a-ariff/ariff-claude-plugins
mkdir -p ~/.claude/skills
cp -r ariff-claude-plugins/plugins/anti-hallucination/skills/anti-hallucination ~/.claude/skills/anti-hallucination

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Anti-Hallucination

/anti-hallucination A verification-hierarchy checklist that catches guessed facts before they're stated.

It also activates on plain-language prompts like these:

Before you answer, please verify that claim against the actual file
Don't guess the function's signature, go check the source file first
What does this CLI flag actually do? Confirm it, don't just assume

Frequently asked questions

Is the Anti-Hallucination skill free?: Yes. The skill itself is free from a-ariff/ariff-claude-plugins. SkillProof publishes the install command and an independent test verdict at no cost.
Does Anti-Hallucination work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Tested · Works. Concrete A/B: asked an unverified guess about a CLI's flag-combination behavior vs. actually reading the 228-line script -- the guess ('probably ignores --title') was wrong, the file shows it throws a hard usage error (exit 2) when --validate is combined with --title/--out-dir/--mode/--input; the skill's own discipline is what catches that gap.
What is the Anti-Hallucination SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 4/5.
How do I install Anti-Hallucination?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Anti-Hallucination with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.