Audit a Claude Code install

    1

    Find the Claude Code failures that produce no error message: dead hooks, rejected skills, missing plugins, oversized memory files.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Audit a Claude Code install

    Example session with this skill installed

    My PostToolUse hook stopped running after I renamed a project directory, and one of my skills never triggers. Nothing shows an error.

    • Read your context and instructions
    • Compiled the audit a claude

    Summary

    8 checks run over ~/.claude. Nothing was created, modified or deleted.

    CheckVerdictEvidence
    settingsParseokvalid JSON
    inlineSecretokno plaintext credential
    apiKeyHelperokcommand resolves
    hookswarnPostToolUse -> ~/.claude/hooks/fmt.sh (file missing)
    skillswarnfrontmatter name "reviewer" != directory "code-review"
    memoryFilewarnCLAUDE.md is 19.8k tokens, injected every turn
    pluginsok4 registered, 4 loadable
    backupswarn2 stale settings copies, each holds the same key

    What to fix first

    1. The PostToolUse hook has not run since the rename — restore or re-point that script.
    2. A skill whose frontmatter name differs from its directory never fires. Rename one to match the other.
    3. CLAUDE.md is a per-turn tax, not a one-time cost. Trim or split it.

    Read-only. Nothing was created, modified or deleted.

    CLAUDE.md

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

    About this skill

    Some Claude Code failures are silent. A hook points at a file that no longer exists. A skill's frontmatter no longer parses, so it is quietly skipped. A plugin is installed but nothing loads it. A CLAUDE.md grew to 20k tokens and is now paid on every single turn.

    None of these produce an error. All of them are checkable.

    This skill runs eight checks over the config directory - settings, hooks, skills, memory files, plugins, backups, transcripts, and credential-shaped values in settings keys that name one - and reports each as ok, warn, or unmeasured.

    Unmeasured is a distinct state, not a pass. A check that could not read anything says so, because "I could not look" and "I looked and it is fine" are different answers.

    Read-only. Node 20+.

    Read-only access only. Requires Node.js >= 20. Cannot modify settings.json or delete backup files. Limited to the ~/.claude directory.

    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

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 2 days ago

    • Free with an Agensi account

    Requires

    Node.js

    Permissions

    Terminal / Shell
    Listed2 days ago

    What's inside

    Frequently Asked Questions

    This skill solves the issue of 'silent failures' where Claude Code features like hooks or custom skills stop working without an error message, often due to broken file paths or invalid metadata.

    The skill is designed specifically for the Claude Code CLI and requires Node.js (version 20+) and Bash to execute diagnostics within the ~/.claude directory.

    No, the skill operates in a strictly read-only mode; it identifies issues like plaintext secrets or invalid paths but will never modify or delete your configuration files.

    Simply run the diagnostic script within your Claude plugin root directory to generate a comprehensive status table covering your settings, hooks, and credentials.

    Your purchase includes the diagnostic runner script, the skill integration package, and a lifetime of updates to ensure compatibility with new Claude Code releases.

    Yes, the 'Credential hygiene' check scans your configuration files and stale backups for plaintext secrets, helping you secure your environment before sharing logs or code.

    New in LLM Ops