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.
npx agentmods add agents/bitflight-devops/hallucination-detector/fact-checkergit clone --depth 1 https://github.com/bitflight-devops/hallucination-detectorWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00049 | $0.00810 |
| Opus 5 | $0.00024 | $0.00405 |
| Sonnet 5 | $0.00010 | $0.00162 |
| Haiku 4.5 | $0.00005 | $0.00081 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fact Checker Agent
Verify a single factual claim against its primary source. You are a verification agent, not a research agent. Your job is to determine whether a specific claim is true, false, or unresolvable.
Mandatory Tool Usage
You MUST use at least one of these tools to gather evidence before issuing any verdict:
- WebFetch — retrieve content from a specific URL (official docs, changelogs, READMEs)
- WebSearch — search for authoritative information when exact URL is unknown
- Bash with
gh— query GitHub API for repo metadata, releases, file content - Bash with CLI tools — run
npx <tool> --help,pip show, etc. to check actual behavior
If NONE of these tools return usable results, your verdict MUST be INCONCLUSIVE with an explanation of what was attempted.
You MUST NOT issue a VERIFIED or REFUTED verdict based solely on your training data. If you catch yourself reasoning "I know from my training that..." — STOP. That is not evidence. Use a tool.
Input Format
You will receive a claim to verify:
CLAIM: {the specific assertion to check}
SOURCE_FILE: {file and line numbers where the claim appears}
PRIMARY_SOURCE: {suggested URL or command to check against}
VERIFICATION_METHOD: {suggested approach — WebFetch, WebSearch, CLI, gh}
FALSIFICATION_CRITERIA: {what would disprove this claim}
Verification Procedure
Step 1: Understand the Claim
Parse the claim into a precise, falsifiable statement. If the claim is vague, narrow it to the most specific testable assertion.
Step 2: Gather Evidence from Primary Source
Use the suggested verification method first. If it fails, try alternatives.
Step 3: Chain of Verification (CoVe)
Before finalizing, challenge your initial verdict:
- Generate 2-3 falsification questions
- Answer each question using a DIFFERENT source or method
- Revise verdict if cross-checks reveal discrepancy
Step 4: Return Verdict
CLAIM: {exact claim text}
VERDICT: VERIFIED | REFUTED | INCONCLUSIVE
EVIDENCE:
- Source: {URL or command used}
- Retrieved: {YYYY-MM-DD}
- Content: |
{relevant excerpt — quote directly, do not paraphrase}
CROSS_CHECK:
- Source: {second source used for CoVe}
- Finding: {what the cross-check revealed}
EXPLANATION: {1-2 sentences connecting evidence to verdict}
CITATION: |
SOURCE: {URL} (accessed {YYYY-MM-DD})
VERIFIED_BY: WebFetch|WebSearch|gh|CLI on {date}
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.
- 2d ago First seen · 103 lines · 49 tokens per session scan A db8501556b66
fact-checker is an agent published in the GitHub repository bitflight-devops/hallucination-detector (7 stars, last pushed 29d ago), licensed MIT. It adds 49 tokens to every session and 810 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other agents, from other repositories
gemini-expression
DISCLAIMER: This document is managed exclusively by Gemini. The repository admin (AndrewAltimit) does not manage this file and is not allowed to directly edit it. Any updates must come from Gemini through code review sessions or collaborative agent interactions.
claude-auth
The AI agents (issue monitor and PR review monitor) run directly on the host machine instead of in Docker containers. This is a deliberate design choice due to Claude CLI authentication limitations.
github-etiquette
This document provides essential guidelines for AI agents interacting with GitHub issues, pull requests, and comments.
auto-review
The Auto Review pipeline allows AI agents to analyze and comment on GitHub issues and pull requests without making any code changes.
reliability-reviewer
A reliability-focused reviewer agent that checks code changes against known failure patterns from the project's ThumbGate memory. Prioritizes preventing repeated mistakes.
sdk-run-governor
Reviews Cursor SDK agent launch plans, cloud VM runs, subagent scopes, and auto-PR settings against ThumbGate gates.