MetaClaw is an AI-agent system that learns from conversations and evolves its behavior over time. It provides memory and learning modes for users who want an agent that adapts across interactions, with support for multiple claw-based agent projects.
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 skills/aiming-lab/metaclaw/avoid-hallucinating-specificsnpx skills add aiming-lab/MetaClaw --skill avoid-hallucinating-specificsgit clone --depth 1 https://github.com/aiming-lab/MetaClawWrote 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/aiming-lab/metaclaw/avoid-hallucinating-specifics)<a href="https://agentmods.dev/skills/aiming-lab/metaclaw/avoid-hallucinating-specifics"><img src="https://agentmods.dev/badge/skills/aiming-lab/metaclaw/avoid-hallucinating-specifics.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 5.1 | $0.00041 | $0.00175 |
| Opus 5 | $0.00020 | $0.00088 |
| Sonnet 5 | $0.00008 | $0.00035 |
| Haiku 4.5 | $0.00004 | $0.00017 |
Grade A, and why
avoid-hallucinating-specifics 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 6d 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
Avoid Hallucinating Specifics
High-risk categories for hallucination:
- Specific API endpoint URLs or request/response schemas.
- Library version numbers and feature availability per version.
- Names of real people, organizations, or publications.
- File paths and environment-specific configuration.
Prevention:
- If unsure of a specific value, say so explicitly.
- Recommend the user verify against official documentation.
- Use
<version>or<your-endpoint>as placeholders rather than guessing.
Anti-pattern: Confidently stating a URL or function signature that sounds right but does not exist.
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.
- 6d ago First seen · 21 lines · 41 tokens per session scan A 1e98934e674a
avoid-hallucinating-specifics is a skill published in the GitHub repository aiming-lab/MetaClaw (3,496 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 175 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 2026-08-30.
Other skills, from other repositories
llama-factory
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support.
tinker-fine-tuning
Provides guidance for fine-tuning LLMs using the Tinker cloud training API from Thinking Machines Lab. Use when running supervised fine-tuning, reinforcement learning (GRPO/PPO), or LoRA training on cloud GPUs via Tinker's managed infrastructure instead of local compute.
tinker-training-cost
Calculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.
transformers
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning…
colab-finetuning
Fine-tune LLMs on Google Colab GPUs directly from openscience. Connects to Colab runtimes via WebSocket bridge for remote training with Unsloth. Supports SFT, GRPO, DPO, vision, and TTS workflows on free T4 to Pro A100 GPUs.
llm-integration
LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.