Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Code Repair Spine: Read-Only Repo Audit

    1

    Generate a source-safe repository audit and repair handoff without mutating your code. Secret scan, risk register, Map of Change, Codex/GPT prompts.

    Free

    3 usesSecurity scanned
    Code Repair Spine: Read-Only Repo Audit

    Code Repair Spine: Read-Only Repo Audit

    Example session with this skill installed

    Generate a repair spine audit for the current local directory and save the reports to ../audit_results.

    • Read your context and instructions
    • Compiled the code repair spine

    Code Repair Spine v0.1 Phase 1 complete.
    Run folder: CRS_my-app_phase1_20231027-1430_a1b2c3d_MED-RISK
    Bundle: 11 artifacts generated (SecretScan, DepGraph, BreakPlan, etc.)
    Status: COMPLETED (read-only)
    Next: Use _handoff/CodexBuildPrompt.md to begin repairs.

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

    About this skill

    Read-only Phase 1 audit for a local repo: inventory, redacted secret scan, Python and JS/TS dependency graphs, risk register, Break Plan, Map of Change, and GPT/Codex repair prompts. Never edits the target repo. Not a security certificate.

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

    Phase 1 only — not an auto-fixer. It plans and scopes the repair; it does not modify code or perform the fix itself.
    Static analysis only. Dependency graphs won't capture dynamic imports, runtime reflection, generated code, bundler aliases, or framework-specific resolution.
    Python and JS/TS dependency graphing only. Other languages get repo inventory and secret scanning, but no dependency graph.
    Secret scan is pattern-based. It flags likely exposures with redacted previews — it can miss novel or obfuscated secrets and may produce false positives. It is not a guarantee that all secrets were found.
    Not a security or compliance certificate. No claim of vulnerability-free, production-safe, or regulatory/compliance conformance.
    Generated prompts are scaffolding, not guaranteed-correct output. The follow-up GPT/Codex/Claude prompts ground the next pass; they don't guarantee the resulting code is correct.
    Does not replace human review. Warnings mean "look here," not "this is broken" or "this is safe."

    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

    3 uses

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 15 days ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell

    File Scopes

    code-repair-spine/**
    Listed5 months ago
    Updated15 days ago

    What's inside

    Frequently Asked Questions

    The Code Repair Spine creates a read-only, structured audit bundle of your repository including dependency graphs and risk assessments, providing a 'source of truth' that prevents AI hallucinations during the repair phase.

    The skill is designed to generate context and prompts compatible with any major LLM, including GPT-4, Claude, and Codex, as well as developer environments like Cursor and Grok.

    Security is built-in; the skill operates strictly in read-only mode and features mandatory secret redaction with salted fingerprints to ensure raw credentials never enter your AI context.

    Yes, while it provides deep analysis for high-level planning, it specifically generates Python and JS/TS dependency graphs to map out architectural constraints.

    You receive the full Code Repair Spine skill, providing you with a standardized workflow to generate 'Break Plans' and 'Maps of Change' for any local repository you are authorized to audit.

    This skill is a Phase 1 audit and planning tool; it summarizes risks and maps the codebase but does not automatically modify, commit, or 'fix' any source code in your repository.

    Free