Agent Standards

    1

    Discover, index, and inject evidence-backed codebase conventions into AI coding agents.

    $15

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    agent-standards

    Example session with this skill installed

    Run discovery on the current directory and then inject standards relevant to "creating a new React functional component with TypeScript props".

    • Read your context and instructions
    • Compiled the agent-standards

    I have mined the codebase for conventions and retrieved the most relevant standards for your React task.

    Standards Injection: React Component Patterns

    IDStandard TitleConsistencyEvidence (Followed/Observed)
    TS-004Use Interface for Component Props92%46/50
    R-012Arrow Function Components100%12/12
    R-015Named Exports for Components85%34/40

    Relevant Context for Your Task

    TS-004: Use Interface for Component Props
    Always define props using an interface named [ComponentName]Props. Do not use type aliases for props.
    Evidence: src/components/Button.tsx, src/components/Card.tsx

    R-012: Arrow Function Components
    Define functional components using const arrow functions. Avoid the function keyword for component definitions.
    Evidence: src/pages/Home.tsx, src/components/Layout.tsx

    R-015: Named Exports for Components
    Use named exports at the bottom of the file or at the point of definition. Avoid export default.
    Evidence: src/utils/helpers.ts, src/components/Input.tsx

    Next steps

    1. Apply TS-004 by creating an interface for your new component props.
    2. Ensure you use a named export as per R-015 to maintain consistency with the src/components directory.
    3. Run agent-standards score <file> after writing the code to verify compliance.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    agent-standards discovers your codebase's real coding conventions from evidence — deterministic AST mining with followed/observed counts — then feeds only the relevant ones to your AI coding agent. Human approval, BM25 retrieval, optional CI enforcement for critical standards, and evals that score whether changed code actually followed them. Works with Claude Code, Cursor, or anything that reads markdown. Local-first, zero API keys. This pack is the ready-to-install skill version: SKILL.md, the full working CLI, shell entrypoint, live dashboard, agent command prompts and tests. Status: experimental / educational. The GitHub version stays free at github.com/k3lick/agent-standards.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Prompt & Skill Engineering.

    Requires Python 3.10+. Minimum 5 observations per pattern required for evidence. Pure shell mode has reduced retrieval quality compared to Python BM25.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 5 days ago

    Software
    Python

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files
    Environment Variables
    Listed5 days ago

    What's inside

    Frequently Asked Questions

    This skill uses AST (Abstract Syntax Tree) mining to scan your existing code for recurring patterns, providing hard data and "followed vs. observed" counts to ensure the agent receives evidence-backed instructions rather than generic guesses.

    It is designed to integrate with any markdown-supported IDE or agent, with specific optimization for Claude Code and Cursor, and includes a Python-based engine (v3.10+) for the discovery phase.

    The package includes the AST mining engine, a CLI for manual rule review, the retrieval-indexed library system, and integration scripts for pre-commit hooks and GitHub Actions.

    Yes, the tool uses BM25 lexical retrieval to dynamically inject only the 3-5 most relevant standards for a specific task, preventing context window bloat and keeping the agent focused.

    The tool supports CI/CD integration, allowing you to set consistency thresholds that trigger build failures if newly generated code deviates from your critical project standards.

    New in Prompt & Skill Engineering