Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    repoctx

    1

    Keep AI agent context files in sync with your code by detecting stale paths and regenerating command tables.

    Free

    1 useSecurity scanned
    repoctx

    repoctx

    Example session with this skill installed

    The project structure changed after the refactor. Audit the agent context files to see if anything is broken and refresh the command tables.

    • Read your context and instructions
    • Compiled the repoctx

    I have audited the repository context files. I found one stale path in AGENTS.md and have regenerated the command tables to reflect the new scripts in your manifest.

    Context health

    File: AGENTS.md · Score: 85/100

    CheckResult
    commands8 claimed, all found
    paths12 referenced, 1 stale

    What to fix

    • src/legacy/utils.ts — referenced in the context file, but the file was deleted or moved during refactor.

    How to fix

    • Update the path in the human-readable section of AGENTS.md, or run repoctx generate . if the command list changed.
    
    # Regenerating code-derived tables...
    repoctx generate .
    
    # Final verification...
    repoctx audit . --check
    

    Next steps

    1. Review the human-written "Conventions" section in AGENTS.md to ensure no manual instructions reference the old src/legacy path.
    2. Commit the updated AGENTS.md to ensure sub-agents stay synced with the new structure.
    AGENTS.md

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

    About this skill

    Context rot kills agent performance. When your AGENTS.md or .cursorrules files claim commands that no longer exist or point to moved paths, your AI model hallucinates and fails. This skill keeps your agent instructions truthful by syncing them with your actual codebase.

    What it does

    • Detects context rot by identifying ghost commands and stale file paths in your agent instructions.
    • Regenerates code tables to automatically update command lists and module dependencies from your manifests.
    • Preserves human content by only modifying sections between specific comment markers.
    • Enforces context health via CI/CD gates that fail when documentation drifts from the implementation.
    • Bootstraps new repos with a standardized context file if one does not exist.

    How it works

    1. Analyze: Run repoctx info to see what manifests, commands, and modules are currently detected in the repository.
    2. Sync: Execute repoctx generate to refresh all code-derived tables while keeping your manual notes intact.
    3. Verify: Use repoctx audit --check to validate that all referenced files and commands actually exist on disk.
    4. Automate: Integrate audit --since into your PR pipeline to catch drift introduced by new changes without failing on legacy debt.

    Frameworks & tools

    Requires the repoctx CLI installed via npm or Homebrew. It works with any repository containing standard manifests and supports AGENTS.md, CLAUDE.md, and .cursorrules files.

    Why this beats prompting it yourself

    Manual updates to agent context files are often forgotten during refactors, leading to "ghost" instructions that mislead the AI. This skill provides a systematic, CLI-backed way to verify facts, ensuring the agent always operates on a valid map of the repository.

    Use cases

    • Syncing AGENTS.md after refactoring scripts in package.json or pyproject.toml.
    • Cleaning up stale file references in .cursorrules after moving documentation folders.
    • Gating pull requests to ensure developers update agent instructions alongside code changes.
    • Auditing inherited codebases to see if the existing agent documentation is still trustworthy.

    Known limitations

    Requires specific repoctx comment markers to modify files. It cannot update human-written sections like project overviews or conventions and requires a manifest file to extract data.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.

    Requires repoctx CLI (npx/brew). Must have a manifest file (package.json, etc.). Only updates content within repoctx comment markers. Cannot auto-fix human-written descriptions.

    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

    1 use

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 25 days ago

    • Free with an Agensi account

    Software
    Node.js

    Permissions

    Read Files
    Write Files
    Listed26 days ago
    Updated25 days ago

    What's inside

    Frequently Asked Questions

    It solves 'context rot' by identifying broken file paths and deleted commands within your agent instructions, ensuring your AI doesn't hallucinate based on outdated information.

    The skill works with any AI agent that consumes local context files, including GitHub Copilot, Cursor, and Claude Dev, by maintaining standard files like AGENTS.md and .cursorrules.

    Yes, repoctx uses specific comment markers to define boundaries, allowing it to regenerate data tables while leaving your manual notes and project conventions completely untouched.

    The skill requires the repoctx CLI to be installed via npm or Homebrew, and it relies on your project's existing manifest files (like package.json or pyproject.toml) to sync data.

    Absolutely. You can integrate the `repoctx audit` command into your CI/CD pipeline to automatically fail Pull Requests if documentation drifts from the actual codebase.

    You receive the full repoctx CLI toolset, a set of standardized context templates for bootstrapping new repositories, and documentation on integrating it into your development workflow.

    New in LLM Ops

    Free