Tag
This project presents version 2 of a cleaned, vendor-neutral system prompt derived from the leaked Claude Fable 5 prompt, offering three variants (Core, Balanced, Complete) to improve cross-model behavior without unnecessary bloat.
A developer distilled the leaked Claude Fable 5 system prompt into a compact 500-token universal Markdown engine for ChatGPT and Gemini, removing Anthropic-specific bloat and making it usable on any frontier model.
Argues that using LangGraph-style orchestration for procedural agent tasks is less effective than simply embedding the full procedure in the system prompt.
Matt Pocock discovers it's trivial to build a proxy for reading raw system prompts sent to Anthropic from Claude Code, and he's now working to remove bloat in the system prompt.
Someone reverse-engineered and open-sourced Claude Design's system prompt, providing a design philosophy and prompt library with a 20-chapter main prompt and 14 skills to improve LLM output quality in UI design.
An open-source system prompt and skill library that turns an LLM into an opinionated, accessibility-aware design collaborator, rejecting common AI design tropes.
Describes shifting from instructing an AI agent with a system prompt to avoid modifying production to implementing actual permission controls.
A practitioner shares 8 months of experience running a voice agent for a law firm, detailing challenges like latency, turn-taking, and post-call workflows, and provides a working system prompt.
A comprehensive guide on 15 moves to leverage Claude's memory architecture, including custom instructions, projects, knowledge files, and system prompts, to avoid re-explaining context in every session.
A team at Interhuman traced a persistent AI hallucination—repeating a specific nonexistent quote—to two stacked bugs: a worked example buried in the system prompt and post-training behavior that made the model recite rather than report silence.
A user reports that Gemini leaked its internal system prompt while attempting to generate a melody, highlighting a potential privacy and security issue.
Maka is a local-first desktop AI workbench whose new feature allows agents to automatically optimize their own system prompts by generating variants, using Harbor container evaluation, and an acceptance policy for iterative improvement, all without human intervention.
Anthropic disputes claims that its Claude Fable 5 model was jailbroken within a day of launch, arguing the researcher's method was coaxing rather than a true breach of core safeguards, and points to extensive bug-bounty testing.
A comprehensive guide explaining the critical role of SOUL.md in Hermes Agent's prompt architecture, covering its placement, content rules, and how to write effective agent personas for different roles while managing token budgets.
A leaked system prompt for Anthropic's Claude Fable 5 model reveals internal behavior instructions and product details, including the new Mythos-class tier and various Claude products.
The user reports that the Gemma 4 12B unified audio model stops attending to speech when the system prompt is large (~21k tokens), and asks for workarounds or explanations, noting the issue persists across vLLM, llama.cpp, and LiteRT-LM backends.
A leaked or user-revealed system prompt for Siri, detailing how the assistant should generate visually rich responses with app-native UI, structured comparisons, and grounded citations, while rejecting redefinition of its capabilities.
Share a Spec Driven Build system prompt for Claude Code and Gemini CLI, letting AI follow a three-phase development process of Requirements → Design → Tasks, designing first before coding to improve code quality.
Discusses how Claude developers lack system prompts, leading to inefficiency, and emphasizes that a good system prompt allows the AI to maintain context and memory across sessions, boosting development efficiency.
The author experiments with using HTML instead of markdown as the primary chat language for AI coding agents, enabling them to render diagrams directly via SVG. The system prompt was rewritten in HTML, improving agent responses with Qwen3.6-27B, and the code is open-sourced.