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/gabrielmoreira/agent-skills-mirrorWrote 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/rules/gabrielmoreira/agent-skills-mirror/agentdock-core)<a href="https://agentmods.dev/rules/gabrielmoreira/agent-skills-mirror/agentdock-core"><img src="https://agentmods.dev/badge/rules/gabrielmoreira/agent-skills-mirror/agentdock-core/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/rules/gabrielmoreira/agent-skills-mirror/agentdock-core"><img src="https://agentmods.dev/badge/rules/gabrielmoreira/agent-skills-mirror/agentdock-core.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 | $0.01683 | $0.01683 |
| Opus 5.5 | $0.00673 | $0.00673 |
| Sonnet 5.5 | $0.00337 | $0.00337 |
| Haiku 4.5 | $0.00168 | $0.00168 |
Grade A, and why
agentdock-core 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 1mo 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.
This is a copy
100% identical to agentdock-core — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentDock Core Framework Rules
This file outlines rules, conventions, and architectural principles for contributing to the agentdock-core directory, the standalone AgentDock framework. Adhering to these guidelines ensures contributions align with the project's goals and future roadmap, facilitating integration into both the open-source project and potential future products.
1. Core Concepts & Purpose
- Foundation:
agentdock-coreis the foundational TypeScript framework, designed to be backend-first, framework-agnostic, and provider-independent. See agentdock-core/README.md for a full overview. - Goal: Enable the creation of sophisticated AI agents capable of complex tasks with configurable determinism.
- Subsystems: Provides modular subsystems for LLM interaction, node/tool execution, session management, orchestration, and pluggable storage/memory.
- Roadmap: Development aims towards supporting advanced memory, vector storage, platform integrations (messaging, voice), multi-agent collaboration, workflow automation, evaluation, and observability. See docs/roadmap.md and detailed files in
[docs/roadmap/](mdc:docs/roadmap). - Status: Pre-release (targeting NPM publication). Contributions should focus on core framework logic.
2. Directory Structure (agentdock-core/src)
Refer to the structure outlined in the agentdock-core/README.md. Key directories house specific subsystems:
[config/](mdc:agentdock-core/src/config): Agent configuration processing and validation.[errors/](mdc:agentdock-core/src/errors): Error handling and standardized error classes.[llm/](mdc:agentdock-core/src/llm): LLM abstraction layer withCoreLLM([core-llm.ts](mdc:agentdock-core/src/llm/core-llm.ts)), provider implementations, model registry ([model-registry.ts](mdc:agentdock-core/src/llm/model-registry.ts)).[logging/](mdc:agentdock-core/src/logging): Structured logging system.[nodes/](mdc:agentdock-core/src/nodes): Base node framework withBaseNode([base-node.ts](mdc:agentdock-core/src/nodes/base-node.ts)),AgentNode([agent-node.ts](mdc:agentdock-core/src/nodes/agent-node.ts)), node registry ([node-registry.ts](mdc:agentdock-core/src/nodes/node-registry.ts)), and tool registry ([tool-registry.ts](mdc:agentdock-core/src/nodes/tool-registry.ts)).[nodes/tool/](mdc:agentdock-core/src/nodes/tool): Tool implementation utilities with base classes and helper functions.[orchestration/](mdc:agentdock-core/src/orchestration): Orchestration and state management.[session/](mdc:agentdock-core/src/session): Session management for conversational state.[storage/](mdc:agentdock-core/src/storage): Storage abstraction with[providers/](mdc:agentdock-core/src/storage/providers)(memory, redis, vercel-kv) and[secure-storage.ts](mdc:agentdock-core/src/storage/secure-storage.ts).[types/](mdc:agentdock-core/src/types): Core TypeScript definitions.[utils/](mdc:agentdock-core/src/utils): Utilities for prompts ([prompt-utils.ts](mdc:agentdock-core/src/utils/prompt-utils.ts)), messages ([message-utils.ts](mdc:agentdock-core/src/utils/message-utils.ts)), LLM operations ([llm-utils.ts](mdc:agentdock-core/src/utils/llm-utils.ts)), and security ([security-utils.ts](mdc:agentdock-core/src/utils/security-utils.ts)).
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.
- 1mo ago First seen · 44 lines · 1,683 tokens per session scan A 72e73e62bde7
agentdock-core is a cursor rule published in the GitHub repository gabrielmoreira/agent-skills-mirror (19 stars, last pushed yesterday), licensed MIT. It adds 1,683 tokens to every session, about $0.0067 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to agentdock-core, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
vue-typescript-patterns
A set of coding rules for Vue 3 projects using TypeScript, a language that adds type checking to JavaScript. It covers component structure, file locations, TypeScript usage, and Pinia, a library for shared application state.
typescript-security
// NEVER: Hardcoded secrets const apiKey = "sk-proj-xxxxx".
nextjs-typescript-app-cursorrules-prompt-file
Cursor rules for Next.js development with TypeScript integration.
ts
A set of TypeScript coding rules covering types, naming, file organization, error handling, and strict type checking. TypeScript is JavaScript with checks that help catch many mistakes before the program runs.
general-rule
Cursor rule "general-rule" from vinhnx/vtchat, covering development guidelines, tech stack & project overview, package management, code style and ui/ux design principles.
platform-pattern-2-filesystem-operations
Cursor rule "platform-pattern-2-filesystem-operations" from PaulJPhilp/EffectPatterns, covering platform pattern 2: filesystem operations and example.