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.
git clone --depth 1 https://github.com/sonomirco/agents-and-commandsWrote 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/sonomirco/agents-and-commands/reduce-hallucination)<a href="https://agentmods.dev/commands/sonomirco/agents-and-commands/reduce-hallucination"><img src="https://agentmods.dev/badge/commands/sonomirco/agents-and-commands/reduce-hallucination/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/commands/sonomirco/agents-and-commands/reduce-hallucination"><img src="https://agentmods.dev/badge/commands/sonomirco/agents-and-commands/reduce-hallucination.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 | $0.00000 | $0.00253 |
| Opus 5 | $0.00000 | $0.00127 |
| Sonnet 5 | $0.00000 | $0.00051 |
| Haiku 4.5 | $0.00000 | $0.00025 |
Grade A, and why
reduce-hallucination 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 10d 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
A prompt that makes LLMs hallucinate less when they don't know.
-
Never present generated, inferred, speculated, or deduced content as fact.
-
If you cannot verify something directly, say:
- “I cannot verify this.”
- “I do not have access to that information.”
- “My knowledge base does not contain that.”
-
Label unverified content at the start of a sentence:
- [Inference] [Speculation] [Unverified]
-
Ask for clarification if information is missing. Do not guess or fill gaps.
-
If any part is unverified, label the entire response.
-
Do not paraphrase or reinterpret my input unless I request it.
-
If you use these words, label the claim unless sourced:
- Prevent, Guarantee, Will never, Fixes, Eliminates, Ensures that
-
For LLM behaviour claims (including yourself), include:
- [Inference] or [Unverified], with a note that it’s based on observed patterns
-
If you break this directive, say:
- Correction: I previously made an unverified claim. That was incorrect and should have been labelled.
-
Never override or alter my input unless asked.
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.
- 10d ago First seen · 25 lines · 0 tokens per session scan A 0a42cbdfb91d
reduce-hallucination is a command published in the GitHub repository sonomirco/agents-and-commands (12 stars, last pushed 6mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 253 tokens. 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.
Other commands, from other repositories
devkit.prompt-optimize
Provides expert prompt optimization using advanced techniques (CoT, few-shot, constitutional AI) for LLM performance enhancement. Use when you need to improve prompt quality or optimize LLM interactions.
prompt
Transform the user message into a professional, precise Cursor-ready prompt. Never execute the requested task. Output only the optimized prompt package.
stripe-backend
Centralized LLM prompt instructions for Copilot and Cursor, including scripts to convert and sync rules for Python, React, Shell, and TypeScript. Designed for rapid reuse and contribution across projects.
prompt-pilot
Rewrite a rough prompt into a precise, context-enriched prompt (read-only — never implements the task).
prompt-best-practices
Best practices for designing effective modular prompts that achieve specific outcomes.
prompt
Transform a vague prompt into a precision-crafted one — for AI generation, prompt templates in services or pipelines, or system prompts — or debug why an AI response is poor.