Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Agent Rules Constitution

    2

    Security & Collaboration Rules for AI Agents

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Agent Rules Constitution

    Agent Rules Constitution

    Example session with this skill installed

    I need to run a script that refactors my local repository and deletes old build artifacts. How should we proceed under the security constitution?

    • Read your context and instructions
    • Compiled the agent rules constitution

    I have reviewed the task against the LOCAL-AGENT-SECURITY-001 baseline. Because this involves filesystem modifications and deletion of files, it falls under the tiered approval framework. I have initialized the pre-flight checks and categorized this as an L3 (High Impact/Non-Reversible) action.

    Security & Execution Plan

    StepActionTool/CommandApproval TierRisk
    1File Discoveryfind . -name "*.build" -o -name "dist"L1 (Read-only)None
    2Refactor Analysisgrep -r "deprecated_pattern" ./srcL1 (Read-only)None
    3Dry Run Refactorsed (piped to temp file)L2 (Reversible)Low
    4Artifact Deletionrm -rf ./dist ./buildL3 (High Impact)Data Loss
    5Commit Changesgit commit -am "Refactor"L2 (Reversible)Medium

    Proposed Safeguards:

    • Path Isolation: All actions are restricted to ~/projects/current-repo/.
    • Audit Trail: Every rm command will be logged to the session history before execution.
    • Rollback: I will create a temporary backup of the dist folder before deletion.

    Next steps

    1. Review the list of detected build artifacts in the next turn.
    2. Provide explicit L3 authorization for the rm -rf command.
    3. Verify the refactoring logic on a single file before I apply it globally.

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

    About this skill

    Your agent can run commands, edit files, browse, and call external services — what stops it from going one step too far? This skill installs a complete, field-tested constitution: a verbatim security baseline (LOCAL-AGENT-SECURITY-001 v1.0) with a deny-by-default permission model, trust boundaries and prompt-injection rules, filesystem and command safety checks, network and data-privacy rules, approval gates, sub-agent containment, audit and recovery discipline, incident response, and honest execution reporting — plus an implementation guide with a four-tier approval reference (L1-L4), an execution workflow, and a cross-session handoff protocol. Works with Claude Code, Cursor, GitHub Copilot, Codex and other agents that read SKILL.md.

    Requires platform-level enforcement (path isolation, network controls) to be truly secure. Does not provide technical sandboxing. Rules must be manually verified as loaded in context.

    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 any payment.

    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 12 days ago

    Permissions

    Read Files
    Write Files
    Listed12 days ago

    What's inside

    Frequently Asked Questions

    This skill provides a structured, versioned constitution that acts as a mandatory safety layer, preventing common agent failures like self-escalation, unauthorized filesystem changes, or "hallucinated completion" of tasks.

    It is platform-agnostic and works with any tool-augmented agent that accepts Markdown instructions, including Claude Code, Cursor, and custom Python-based agentic loops.

    You will receive the authoritative Security Policy, a Tiered Implementation Guide for approval workflows, and a Session Handoff Protocol to maintain security across long-running tasks.

    No, this is a logic-based security framework; while it sets the rules for safe execution, you are still responsible for providing the technical sandbox or containerized environment where the agent operates.

    Simply load the provided Markdown documents into your agent's system context or reference them in your global configuration to establish the 'deny-by-default' boundary immediately.

    The constitution is designed for agents with high-level permissions, such as those using 'sudo', 'rm', or 'curl', ensuring they pause for L1-L4 user consent before performing non-reversible actions.

    New in Agents & Orchestration