anti-hallucination-techniques

anti-hallucination-techniques is a skill for Claude Code, Codex from Omar-Obando/qwen-orchestrator. It costs 56 tokens per session (2,004 once invoked), scanned A, original, MIT.

Guidance for checking whether claims, sources, citations, code examples, and technical information are accurate. It focuses on evidence and source credibility to reduce made-up or unsupported answers.

In plain words
What is it for?
Fact-checking generated text, validating technical examples and specifications, checking citations and sources, and reviewing claims about science, law, finance, medicine, or other factual topics.
Why use it?
It helps catch incorrect AI output and other unreliable information before it reaches documentation, code, decisions, or users.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Fact-checking generated text, validating technical examples and specifications, checking citations and sources, and reviewing claims about science, law, finance, medicine, or other factual topics.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/omar-obando/qwen-orchestrator/anti-hallucination-techniques
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.

Any agent
npx skills add Omar-Obando/qwen-orchestrator --skill anti-hallucination-techniques
Clone the repo
git clone --depth 1 https://github.com/Omar-Obando/qwen-orchestrator

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for anti-hallucination-techniques

README.md
[![agentmods](https://agentmods.dev/badge/skills/omar-obando/qwen-orchestrator/anti-hallucination-techniques/github.svg)](https://agentmods.dev/skills/omar-obando/qwen-orchestrator/anti-hallucination-techniques)
Your own site
<a href="https://agentmods.dev/skills/omar-obando/qwen-orchestrator/anti-hallucination-techniques"><img src="https://agentmods.dev/badge/skills/omar-obando/qwen-orchestrator/anti-hallucination-techniques/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.

agentmods 80×15 button for anti-hallucination-techniques

Your own site · 80×15
<a href="https://agentmods.dev/skills/omar-obando/qwen-orchestrator/anti-hallucination-techniques"><img src="https://agentmods.dev/badge/skills/omar-obando/qwen-orchestrator/anti-hallucination-techniques.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,004 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.02004
Opus 5 $0.00028 $0.01002
Sonnet 5 $0.00011 $0.00401
Haiku 4.5 $0.00006 $0.00200

Measured 12d ago against content hash 67fef762ad5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

anti-hallucination-techniques 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.

skills/anti-hallucination-techniques/SKILL.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Anti-Hallucination Techniques Skill — Doc Researcher

Overview

This skill provides comprehensive guidance for preventing and detecting AI hallucinations. It covers source verification, evidence-based reasoning, fact-checking techniques, and validation frameworks following information verification best practices and AI safety guidelines.

When to Use

Use this skill when:

  • Verifying AI-generated content accuracy
  • Checking source credibility and citations
  • Validating claims with evidence
  • Implementing evidence-based reasoning
  • Detecting and correcting hallucinations
  • Fact-checking technical documentation
  • Validating code examples
  • Checking API documentation accuracy
  • Verifying configuration examples
  • Validating architectural diagrams
  • Checking mathematical calculations
  • Validating statistical claims
  • Verifying historical facts
  • Checking product specifications
  • Validating legal or compliance information
  • Checking financial data
  • Verifying medical or health information
  • Validating scientific claims
  • Checking technical specifications
  • Verifying geographic information
  • Validating dates and times
  • Checking names and proper nouns
  • Validating contact information

Do NOT use this skill when:

  • Writing application business logic (use domain-driven skill)
  • Designing database schemas (use database-design skill)
  • Writing API endpoint specifications (use api-design skill)
  • Performing security audits (use security-auditor skill)
  • Writing SQL queries (use sql-best-practices skill)
  • Designing multi-page website layouts (use design-system skill)
  • Analyzing deployment configurations (use deployment skill)
  • Writing documentation (use documentation-best-practices skill)

Hallucination Types

Common Hallucination Patterns

┌─────────────────────────────────────────────────────────────┐
│              Hallucination Types                            │
├─────────────────────────────────────────────────────────────┤
│  1. Factual Hallucinations                                  │
│     - Incorrect dates, names, numbers                       │
│     - False historical claims                               │
│     - Misrepresented statistics                             │
│                                                              │
│  2. Technical Hallucinations                                │
│     - Incorrect API usage                                   │
│     - Fake function signatures                              │
│     - Non-existent libraries                                │
│                                                              │
│  3. Logical Hallucinations                                  │
│     - Invalid reasoning                                     │
│     - False cause-effect relationships                      │
│     - Contradictory statements                              │
│                                                              │
│  4. Source Hallucinations                                   │
│     - Fake citations                                        │
│     - Non-existent URLs                                     │
│     - Fabricated sources                                    │
│                                                              │
│  5. Pseudo-Quantification                                   │
│     - Made-up statistics                                    │
│     - Unsubstantiated percentages                           │
│     - False measurements                                    │
└─────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 262 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 262 lines · 56 tokens per session scan A 67fef762ad5b

Subscribe to this mod's changes

anti-hallucination-techniques is a skill published in the GitHub repository Omar-Obando/qwen-orchestrator (49 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 2,004 once invoked, about $0.0003 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 2026-08-30.