Agent Instructions Doctor

    1

    Audit and repair decaying agent instruction files to fix contradictions, stale rules, and token bloat.

    Free

    7 usesSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Agent Instructions Doctor

    Example session with this skill installed

    Audit my .cursorrules and CLAUDE.md files. The agent keeps using Yarn even though we switched to pnpm, and the context feels bloated.

    • Read your context and instructions
    • Compiled the agent instructions doctor

    Found 3 contradictions. 🔴 Actively harmful: .cursorrules line 12 references 'yarn install' while CLAUDE.md line 4 says 'use pnpm'. 🟡 Expensive: 400 tokens used for 'be thoughtful' prose. Proposed diff: update all commands to pnpm and convert prose to actionable decision-point lists.

    line 12 references 'yarn install' while CLAUDE.md

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

    About this skill

    The problem

    Instruction files like CLAUDE.md or .cursorrules decay into "token scar tissue" over time. Agents start ignoring rules, behaving inconsistently, or hallucinating based on stale conventions for retired frameworks.

    What it does

    • Identifies direct and partial contradictions across multiple instruction files like AGENTS.md and .cursorrules.
    • Cross-checks rules against the actual repository to find dead paths, missing scripts, and retired framework references.
    • Flags "token bloat" and unenforceable rules that consume context without changing agent behavior.
    • Audits instruction placement to ensure high-priority rules are positioned where the LLM is most likely to attend to them.
    • Generates a prioritized report of harmful, inert, and missing instructions with ready-to-paste diffs.

    Frameworks & tools

    Works with Cursor (.cursorrules), Claude Dev/Roo Code (CLAUDE.md), GitHub Copilot (.github/copilot-instructions.md), and generic project AGENTS.md files.

    Why this beats prompting it yourself

    Manually auditing 2,000 tokens of rules for logical consistency is error-prone. This skill performs a multi-pass analysis that specifically checks for "hidden overrides" in nested directories that a standard prompt would likely miss.

    Use cases

    • Fixing an agent that keeps using the wrong library version despite instructions.
    • Reducing token costs in large monorepos with bloated context files.
    • Onboarding a new agent to a legacy project with outdated documentation.
    • Consolidating fragmented rules from three different editor-specific config files.

    Known limitations

    Does not access external networks. It analyzes and edits instruction files only, not the underlying application logic.

    Analyzes local files only. Does not remove unusual rules without confirmation, as these are often project-specific edge cases.

    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

    7 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 3 months ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed3 months ago

    What's inside

    Frequently Asked Questions

    The Instructions Doctor identifies conflicting rules, outdated framework references, and 'token bloat' that causes agents to ignore instructions. It provides a prioritized report with ready-to-paste diffs to streamline your files for better LLM performance.

    It is fully compatible with major AI coding assistants including Cursor (.cursorrules), Claude Dev/Roo Code (CLAUDE.md), and GitHub Copilot, as well as custom AGENTS.md files.

    Yes, the skill is specifically designed to perform multi-pass audits across nested directories to identify 'hidden overrides' where local rules might be contradicting global project instructions.

    No, the skill operates locally on your instruction files to ensure privacy and security. It analyzes and repairs your documentation and configuration logic without accessing your external network or application data.

    Simply add the skill to your agent's workflow and point it toward your project root. It will automatically scan for known instruction file formats and generate an audit report without any complex manual configuration.

    New in Agents & Orchestration