Skill Doctor Free Version

    1

    Saving money from unnecessary tokens

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Skill Doctor Free Version

    Example session with this skill installed

    My agent is getting expensive and slow. Run a health check on my skills to see if we can save some tokens.

    • Read your context and instructions
    • Compiled the doctor free version

    I have performed a read-only audit of your installed skills. You are currently spending 1,450 tokens on every model step just for skill descriptions. Two skills are shadowed, meaning their duplicates are wasting space without being accessible.

    Skill Audit Results

    FindingSkill IDImpactRecommendation
    token-budgetdata-analyzer-pro450 tokens/stepTrim description or set autoinvoke: false
    shadowedgit-helperRedundant loadArchive the duplicate in ./old_skills/
    long-descriptionweather-api210 tokens/stepCondense the 3-paragraph summary
    broken-referencepdf-parserExecution failFix missing path in references/

    Estimated Savings
    If you apply the recommended fixes, you will save

    660 tokens per step. Over a typical 100-step session, this saves 66,000 tokens.

    Next steps

    1. Run npx -y opencode-skills-doctor fix --hide data-analyzer-pro to stop advertising the largest skill.
    2. Allow me to archive the shadowed git-helper duplicates.
    3. Review the weather-api description to shorten it to one sentence.

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

    About this skill

    Large agent skill libraries eventually degrade performance. Context bloat from excessive skill descriptions increases token costs on every model step and leads to shadowed duplicates or broken references. This tool audits your installed skills to reclaim context window and reduce operational costs.

    What it does

    • Token Auditing measures the per-step cost of all advertised skill descriptions to find budget overruns.
    • Conflict Detection identifies shadowed skill IDs where duplicates exist in multiple locations.
    • Health Monitoring checks for broken references to external scripts or required files.
    • Optimization Planning calculates potential token savings by trimming descriptions or toggling auto-invocation.
    • Actionable Fixes generates commands to hide low-frequency skills or archive redundant duplicates.

    How it works

    1. Run Check executes a read-only JSON audit to identify specific findings like token-budget or shadowed.
    2. Review Savings generates a plan to show how many tokens can be saved per 100 model steps.
    3. Execute Fix applies targeted commands to hide or archive skills based on your confirmation.
    4. Verify Health re-runs the check to confirm the new, lower operational cost.

    Frameworks & tools

    Built for agents using the opencode-skills-doctor CLI via Node.js/npx. It processes local skill directories and SKILL.md files.

    Why this beats prompting it yourself

    Manual token counting across dozens of markdown files is error-prone and tedious. This skill uses a specialized CLI to provide precise, data-driven savings calculations that an LLM cannot accurately estimate through raw text analysis alone.

    Use cases

    • Identify which skills are bloating the system prompt and costing money on every turn.
    • Resolve "shadowed" skill errors where the wrong version of a tool is being loaded.
    • Debug missing script references after moving skill folders.
    • Prune a large library of skills to stay within the model's context window limits.

    Known limitations

    Requires Node.js and npx to be available in the execution environment. It cannot modify skill files without user confirmation.

    Requires Node.js/npx installed. Cannot resolve internal logic errors within a skill's body, only structural and token-based issues.

    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 4 days ago

    • Free with an Agensi account

    Requires

    Node.js
    opencode-skills-doctor
    Skills Doctor MCP

    Permissions

    Read Files
    Write Files
    Network Access
    Environment Variables
    Terminal / Shell
    Browser
    Listed4 days ago

    What's inside

    Frequently Asked Questions

    This skill identifies 'context bloat'—excessive token usage caused by large skill libraries—and resolves 'shadowed' conflicts where duplicate skill IDs cause the agent to call the wrong version of a tool.

    The skill is built for agents utilizing the `opencode-skills-doctor` CLI and is compatible with any local environment where Node.js and npx are available. It primarily audits local skill directories and SKILL.md files.

    No, the tool operates in a read-only state during the audit phase; it identifies issues and calculates potential savings, but only applies fixes or archives files after you review and confirm the proposed plan.

    You receive the 'terminal report' skill package, which includes the integration for the `opencode-skills-doctor` CLI and pre-configured routines for token auditing, conflict detection, and optimization planning.

    If you move folders or rename dependencies, run the Health Monitoring check; it specifically scans for broken references to external scripts or missing required files that cause skills to fail during execution.

    New in LLM Ops