hallucination-detector

A stop-hook plugin that checks an AI assistant’s output for unsupported claims, speculation, invented measurements, and statements that claim more completeness than the evidence allows.

In plain words
What is it for?
Use it to audit coding-agent responses for hallucinated behavior, unjustified cause-and-effect claims, fake precision, or unsupported claims that a task is fully complete.
Why use it?
It interrupts completion when an answer needs stronger evidence or a more careful wording. This helps keep generated responses grounded in what is actually known.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add bitflight-devops/hallucination-detector
agentmods
npx agentmods add plugins/bitflight-devops/hallucination-detector/hallucination-detector
Clone the repo
git clone --depth 1 https://github.com/bitflight-devops/hallucination-detector

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

hallucination-detector 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 2d 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.

.claude-plugin/plugin.json · 23 lines

What it actually says

{
  "name": "hallucination-detector",
  "displayName": "Hallucination Detector",
  "description": "Stop-hook that audits assistant output for speculation, ungrounded causality, pseudo-quantification, and completeness overclaims — blocks completion to force evidence-first rewrites",
  "version": "1.18.2",
  "author": {
    "name": "Jamie Nelson",
    "url": "https://github.com/bitflight-devops"
  },
  "homepage": "https://github.com/bitflight-devops/hallucination-detector",
  "repository": "https://github.com/bitflight-devops/hallucination-detector",
  "license": "MIT",
  "keywords": [
    "hallucination",
    "speculation",
    "causality",
    "verification",
    "stop-hook",
    "quality"
  ],
  "commands": "./commands/"
}
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. 2d ago First seen · 23 lines scan A 09cfac4dd064

Subscribe to this mod's changes

hallucination-detector is a plugin published in the GitHub repository bitflight-devops/hallucination-detector (7 stars, last pushed 29d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.