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 commands/bitflight-devops/hallucination-detector/hallucination-auditgit clone --depth 1 https://github.com/bitflight-devops/hallucination-detectorWrote 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.
[](https://agentmods.dev/commands/bitflight-devops/hallucination-detector/hallucination-audit)<a href="https://agentmods.dev/commands/bitflight-devops/hallucination-detector/hallucination-audit"><img src="https://agentmods.dev/badge/commands/bitflight-devops/hallucination-detector/hallucination-audit.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00029 | $0.00453 |
| Opus 5 | $0.00015 | $0.00227 |
| Sonnet 5 | $0.00006 | $0.00091 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
hallucination-audit 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 4d 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.
What it actually says
Hallucination Audit
INPUT: Paste the target content to audit (assistant output, sub-agent output, or a draft response).
Review the target content for these HALLUCINATION TRIGGERS:
1. Speculation Language (Guessing Trigger)
Scan for: "I think", "likely", "probably", "seems", "should be", "assume", "maybe", "might".
Action: FLAG. Replace with one of:
- "I don't know yet."
- "I don't have that information."
- "This is something I can check using my tools."
- "I did these steps: . I observed: ."
2. Causality Without Evidence (Diagnosis Trigger)
Scan for: "because", "due to", "caused by", "therefore", "this means", "as a result".
Action: If the sentence does not cite a specific observation (tool output, logs, file lines, measured behavior), FLAG. Rewrite as:
- Observation-only statement, OR
- Explicit hypothesis + next verification step (no causal claim yet).
3. Pseudo-Quantification (Fake Rigor Trigger)
Scan for: scores/percentages like "8.5/10", "70% improvement", "100%".
Action: If no methodology + evidence is shown, FLAG. Replace with measurable evidence or remove.
4. Completeness Claims (Overreach Trigger)
Scan for: "all files checked", "comprehensive analysis", "fully resolved", "everything fixed".
Action: FLAG unless the content explicitly lists the concrete checks performed (what was inspected, with what scope).
5. Delegation Micromanagement (Prescription Trigger)
Scan for: overly specific prescriptive edits in delegation prompts ("change line 42", "rename variable X to Y") when not required by the user.
Action: Replace with success criteria + constraints + verification steps.
OUTPUT:
- Pass/Fail.
- If Fail: quote the exact triggering phrase(s) and provide the required rewrite.
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.
- 4d ago First seen · 53 lines · 29 tokens per session scan A 39ecd204ba99
hallucination-audit is a command published in the GitHub repository bitflight-devops/hallucination-detector (7 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 453 once invoked, about $0.0001 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 commands, from other repositories
ai-act-incidents
Show real-world and research-demonstrated security incidents that map to a scanner dimension, EU AI Act article, or threat category. Surfaces OWASP LLM/ASI, NIST AI RMF, and MITRE ATLAS cross-references alongside published mitigations.
ai-act-scan
Scan a codebase for EU AI Act compliance evidence and gaps. Produces a dimension-scored report with per-file findings, architecture graph, and prioritized recommendations.
ai-act-article
Show which analyzers, compliance dimensions, and current findings in this codebase map to a specific EU AI Act article.
ai-act-ask
Answer an EU AI Act question grounded in the bundled knowledge base — verbatim statute text, obligation paraphrases, and the compound-risk taxonomy. Offline and deterministic by default; cites the articles it relies on.
ai-act-settings
View or change the scanner's settings — mode (deterministic vs assisted) and autoapply. Assisted mode lets the plugin use your own Claude Code for semantic scanning, grounded Q&A, and applying fixes.
ai-act-scan-fix
Scan a codebase, then propose concrete remediation (code edits, new files, tests) for the top compliance gaps. Does NOT auto-apply — always shows the plan first.