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 skills add Notysoty/openagentskills --skill hallucination-risk-reviewergit clone --depth 1 https://github.com/Notysoty/openagentskillsWrote 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/skills/notysoty/openagentskills/hallucination-risk-reviewer)<a href="https://agentmods.dev/skills/notysoty/openagentskills/hallucination-risk-reviewer"><img src="https://agentmods.dev/badge/skills/notysoty/openagentskills/hallucination-risk-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/notysoty/openagentskills/hallucination-risk-reviewer"><img src="https://agentmods.dev/badge/skills/notysoty/openagentskills/hallucination-risk-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00029 | $0.01960 |
| Opus 5 | $0.00015 | $0.00980 |
| Sonnet 5 | $0.00006 | $0.00392 |
| Haiku 4.5 | $0.00003 | $0.00196 |
Grade A, and why
Hallucination Risk Reviewer 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 12d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hallucination Risk Reviewer
What this skill does
This skill reviews an LLM-generated response or the output of an AI-powered application feature to assess its hallucination risk. It identifies the specific types of claims that are most likely to be fabricated, flags confidence calibration issues (the model sounds certain about things it may not know), and recommends mitigations. The output is a structured risk assessment that helps you decide whether to use the output as-is, verify specific claims, or redesign the prompt/system.
Use this when building AI-powered features where factual accuracy matters, when reviewing generated content before publishing, or when evaluating whether an LLM is suitable for a high-stakes use case.
How to use
Claude Code / Cline
Copy this file to .agents/skills/hallucination-risk-reviewer/SKILL.md in your project root.
Then ask:
- "Use the Hallucination Risk Reviewer skill on this AI-generated response: [paste response]."
- "Review the outputs of our AI support bot for hallucination risk using the Hallucination Risk Reviewer skill."
Provide:
- The AI-generated text or a sample of outputs
- The original prompt or context given to the model (if known)
- The use case (what decision or action will this output inform?)
- The model or system used (if known)
Cursor
Add the instructions below to your .cursorrules or paste them into the Cursor AI pane. Provide the output to review.
Codex
Paste the AI output and context. Ask Codex to follow the instructions below.
The Prompt / Instructions for the Agent
When asked to review for hallucination risk, follow this framework:
Step 1 — Identify the claim types
Read the output and categorize every substantive claim into one of these types:
Factual claims about the world
- Named events, dates, statistics, scientific findings
- Quotes attributed to real people
- Historical facts
- Product features, pricing, availability
- Legal or regulatory information
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.
- 12d ago First seen · 201 lines · 29 tokens per session scan A ec38bc82f315
Hallucination Risk Reviewer is a skill published in the GitHub repository Notysoty/openagentskills (9 stars, last pushed 28d ago), licensed MIT. It adds 29 tokens to every session and 1,960 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 skills, from other repositories
llm-engineering-expert
Build reliable applications on large language models: prompt design, structured output, evaluation, guardrails, and cost and latency control. Use when the user mentions LLMs, prompts, prompt engineering, few-shot examples, structured or JSON output, function calling, hallucination, model evaluation, token costs…
dspy-evaluation-suite
Use for evaluating DSPy programs with Evaluate, answerexactmatch, SemanticF1, custom metrics, baselines, and program comparisons.
dspy-output-refinement-constraints
Use for dspy.Refine, dspy.BestOfN, output constraints, validation, reward functions, and iterative output refinement.
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…