Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Checkpoint Doctor

    1

    Audit the directory where your agent keeps session state before trusting a resume: empty files, ambiguous duplicates, truncated JSON, clock skew, stale state and credentials sitting in plain text.

    Free

    1 useSecurity scanned

    About this skill

    A resume goes wrong in ways that look fine from the outside: the state file exists but is empty, two files describe the same task and the loader picks one at random, a timestamp is a month in the future, or the "state" quietly contains an API key. All of it is invisible until a session resumes onto stale or wrong context.

    This is the 400-line check you run before the resume — and before you paste a state file anywhere.

    Exit codes: 0 clean · 1 findings · 2 nothing to audit (explicit: not found, or no state files — an empty scan is not a clean result) · 4 usage error.

    FindingWhy it matters
    empty_state_filea resume reads silence and concludes the work is done
    possible_duplicate_statetwo files with the same top-level keys → the loader picks arbitrarily
    unparseable_jsontruncated write (killed mid-write) — the state is gone, not "almost there"
    timestamp_in_the_futureclock skew; "newest wins" becomes a coin flip
    stale_stateolder than --max-age-days: verify against the live system before trusting it
    secret_like (high)private key blocks, sk-…, ghp_…, AKIA…, JWTs, api_key: … in plain text
    high_entropy_string (medium)a 40+ char random-looking token the named patterns missed

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    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 1 month ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Audit the directory where your agent keeps session state before trusting a resume: empty files, ambiguous duplicates, truncated JSON, clock skew, stale state and credentials sitting in plain text.

    This skill uses the open SKILL.md standard. Use it through an MCP-compatible agent connected to Agensi, and check the compatibility information on this page for confirmed agents and required capabilities.

    Connect your AI agent to Agensi through MCP, then ask it to use Checkpoint Doctor on your task. Your agent loads the latest approved version each time. Paid skills require a purchase or active subscription. Skill files are not available for download; your licence does not allow you to save, copy or export any part of a skill.

    New in Agents & Orchestration

    Free