#prompt-engineering

The Agency is a growing collection of meticulously crafted AI agent personalities. Each agent is:

🎯 Specialized: Deep expertise in their domain (not generic prompt templates)
🧠 Personality-Driven: Unique voice, communication style, and approach
📋 Deliverable-Focused: Real code, processes, and measurable outcomes
✅ Production-Ready: Battle-tested workflows and success metrics

Think of it as: Assembling your dream team, except they're AI specialists who never sleep, never complain, and always deliver.

AI SYSTEMS TRANSPARENCY AND OBSERVABILITY FOR ALL! Full extracted system prompts, guidelines, and tools from OpenAI, Google, Anthropic, xAI, Perplexity, Cursor, Windsurf, Devin, Manus, Replit, and more – virtually all major AI models + agents!

rtk filters and compresses command outputs before they reach your LLM context. Single Rust binary, 100+ supported commands, <10ms overhead.

A Claude Code skill/plugin that makes agent talk like caveman — cuts ~75% of output tokens, keeps full technical accuracy. Brain still big. Mouth small.

git clone https://github.com/JuliusBrussee/caveman.git
cd caveman

node bin/install.js --only claude --minimal

Interesting prompt for porting zig to rust in bun.

At Lasso, we have been building Intent Security, a runtime security framework that ensures every component in the agentic system behaves as intended. It monitors the behavior of each component and analyzes their alignment. Like auto mode, when alignment holds it allows actions to proceed. When misalignment is detected, it intervenes. When we read Anthropic's post, the overlap in core assumptions was hard to miss. This post provides a comparison of the two approaches.

Independent evaluation without cross-contamination is what enables misalignment detection.

‍Anthropic's input layer screens external content for injection attempts before it reaches the agent to determine whether tool outputs are safe. The output layer structurally evaluates whether the agent's tool calls are aligned with user intent. Critically, the output classifier never sees tool results, to prevent compromised external content from influencing the security decision.

Anthropic publishes the history of system prompts used on claude.ai and the mobile apps at https://platform.claude.com/docs/en/release-notes/system-prompts. That page is a single monolithic markdown document grouped by model, and each model lists one or more dated revisions.

Extracted system prompts from Anthropic - Opus 4.7, Opus 4.6, Sonnet 4.6. OpenAI - ChatGPT 5.5 Thinking, GPT 5.5 Instant, Codex. Google Gemini - 3.5 Flash, 3.1 Pro, 3 Flash, Antigravity. xAI - Grok. Github Copilot. Perplexity, and more. Updated regularly.

nd what most people dont realize is that YAML's human-friendly formatting comes with a hidden cost, it uses more tokens than JSON for the exact same data, which means you're literally paying extra for those nice indentations and lack of brackets.

YAML consistently uses 6-10% more tokens than JSON for identical data

Some models actually perform better with YAML despite the higher token count. Nova models in particular showed this weird preference. Meanwhile, Claude models generally performed better with JSON.

Sonnet 4 scored 93.3% with JSON and 76.7% with YAML, while Opus 4.1 only managed 73.3% with JSON and 66.7% with YAML.

Something interesting I noticed while analyzing the data, by stripping out unnecessary GitHub metadata (stuff like URLs, IDs, and fields you'll never use), you could reduce your token count by up to 80%. Thats not a typo. EIGHTY PERCENT.

For proprietary agents that don’t want to join in, good old symlinks do the job:

Fix A Broken AGENTS.md With This Prompt

If you're starting to get nervous about the AGENTS.md file in your repo, and you want to refactor it to use progressive disclosure, try copy-pasting this prompt into your coding agent:

I want you to refactor my AGENTS.md file to follow progressive disclosure principles.

Follow these steps:

1. Find contradictions: Identify any instructions that conflict with each other. For each contradiction, ask me which version I want to keep.

2. Identify the essentials: Extract only what belongs in the root AGENTS.md:

   • One-sentence project description
   • Package manager (if not npm)
   • Non-standard build/typecheck commands
   • Anything truly relevant to every single task

3. Group the rest: Organize remaining instructions into logical categories (e.g., TypeScript conventions, testing patterns, API design, Git workflow). For each group, create a separate markdown file.

4. Create the file structure: Output:

   • A minimal root AGENTS.md with markdown links to the separate files
   • Each separate file with its relevant instructions
   • A suggested docs/ folder structure

5. Flag for deletion: Identify any instructions that are:

   • Redundant (the agent already knows this)
   • Too vague to be actionable
   • Overly obvious (like "write clean code")

Write the built‑in prompt to the project default path:

GEMINI_WRITE_SYSTEM_MD=1 gemini

Write the built‑in prompt to the project default path:

GEMINI_WRITE_SYSTEM_MD=1 gemini

An open source toolkit that allows you to focus on product scenarios and predictable outcomes instead of vibe coding every piece from scratch.

Subscribe [On agents using CLI tools in place of REST APIs] To save on context window, yes, but moreso to improve accuracy and success rate when multiple tool calls are involved, particularly when calls must be correctly chained e.g. for pagination, rate-limit backoff, and recognizing authentication failures.

Other major factor: which models can wield the skill? Using the CLI lowers the bar so cheap, fast models (gpt-5-nano, haiku-4.5) can reliably succeed. Using the raw APl is something only the costly "strong" models (gpt-5.2, opus-4.5) can manage, and it squeezes a ton of thinking/reasoning out of them, which means multiple turns/iterations, which means accumulating a ton of context, which means burning loads of expensive tokens. For one-off API requests and ad hoc usage driven by a developer, this is reasonable and even helpful, but for an autonomous agent doing repetitive work, it's a disaster.

For every complex task, create THREE files:

task_plan.md → Track phases and progress notes.md → Store research and findings [deliverable].md → Final output

The Loop

1. Create task_plan.md with goal and phases
2. Research → save to notes.md → update task_plan.md
3. Read notes.md → create deliverable → update task_plan.md
4. Deliver final output

Key insight: By reading task_plan.md before each decision, goals stay in the attention window. This is how Manus handles ~50 tool calls without losing track.

If you find yourself writing a prompt for something repetitively and instructions can be static/precise, it's a good idea to make a custom command. You can tell Claude to make custom commands. It knows how (or it will search the web and figure it out via claude-code-guide.md) and then it will make it for you.

The Explore agent is a read-only file search specialist. It can use Glob, Grep, Read, and limited Bash commands to navigate codebases but is strictly prohibited from creating or modifying files.

You will notice how thorough the prompt is in terms of specifying when to use what tool call. Well, most people underestimate how hard it's to make tool calling work accurately.

Context engineering is about answering "what configuration of context is most likely to generate our model's desired behavior?"

Extracting Claude’s soul.

Antigravity is Google’s new agentic code editor. In this article, we demonstrate how an indirect prompt injection can manipulate Gemini to invoke a malicious browser subagent in order to steal credentials and sensitive code from a user’s IDE.

Google’s approach is to include a disclaimer about the existing risks, which we address later in the article.

Fascinating prompt engineering and injection (harmless).