production readiness audit

Production readiness is often a subjective "gut feeling" that leaves teams vulnerable to outages and exploits. This skill replaces guesswork with a formal eight-lens audit that evaluates whether a codebase is actually ready for real users, real attackers, and real load. It treats the absence of critical systems—like monitoring, rate limiting, or backups—as high-severity findings, ensuring you never ship a system that is fundamentally incomplete.

What it does

• Multi-perspective auditing scans the repo using eight specialized lenses including security, backend, devops, and database.
• Evidence-based reporting requires every finding to cite specific code lines or ledger entries, preventing vague or hallucinated issues.
• Automated dashboarding launches a local web interface to visualize the audit trail, findings, and final go/no-go verdict.
• Absence detection uses a dedicated ledger to track what was searched for but not found, flagging missing infrastructure-as-code or controls.
• Runtime validation performs read-only inspections of live staging environments to confirm environment-specific configurations.

How it works

1. Context Intake: Define the system criticality, RTO/RPO targets, and threat model to calibrate finding severity.
2. Evidence Pass: Run deterministic probes to build a semantic map and inventory of existing controls and missing patterns.
3. Lens Dispatch: Launch parallel specialist agents to evaluate the evidence and generate tagged findings (CONFIRMED, NOT FOUND, or UNVERIFIED).
4. Validation & Reporting: Verify findings against formal rules and generate a CTO-ready Markdown report and JSON verdict.

Frameworks & tools

This skill utilizes a suite of internal Python scripts for state management (audit_state.py), evidence gathering (evidence_scan.py), and validation (validate_findings.py). It is designed to run in environments like Claude Code or Cursor with access to local files and a Python 3 runtime.

Why this beats prompting it yourself

Generic prompts often miss what is NOT there, which is where most production failures start. This skill enforces a strict evidence ledger and a multi-agent "lens" architecture that prevents a single agent from overlooking cross-disciplinary gaps. It provides a persistent, structured audit trail under .readiness-audit/ rather than a fleeting chat response.

Use cases

• Auditing a repository before a major production launch or migration.
• Performing a technical due diligence review of a new codebase.
• Identifying scalability bottlenecks and security gaps during a 10x load prep.
• Providing an objective go/no-go report for engineering leadership.

Known limitations

This skill is strictly read-only and will not fix the issues it finds. It requires a local Python 3 environment to run the underlying orchestration and dashboard scripts.