Menu
Audit an application against Twelve-Factor and modern 12+ Factor criteria with structured evidence, risks, and remediation tasks.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Generate a corpus snapshot report — computes dimensions, topology, degree distribution, delta from previous. Helps with cluster, chain, and gap analysis sections.
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor
Orchestrate multi-loop background operations via the Mission Control dashboard — start sessions, dispatch missions, monitor, and stop
Launch an AIWG Mission — durable, audited dynamic agent orchestration toward a completion criterion. AIWG owns the conductor (activity-log, gates, best-output, checkpoint/resume, cost); native primitives drive worker mechanism. Surfaces as /aiwg-mission in Codex (AIWG-owned, no plugin dependency).
Config-driven release orchestration — reads .aiwg/release.config plus optional .aiwg/releases/<plan-id> sidecars and walks the selected release plan's gates
Update AIWG CLI and redeploy frameworks/tools to current project without leaving the session
| namespace | aiwg |
| name | twelve-factor-audit |
| description | Audit an application against Twelve-Factor and modern 12+ Factor criteria with structured evidence, risks, and remediation tasks. |
| platforms | ["all"] |
| triggers | ["twelve factor audit","12 factor audit evidence","audit application against 12+ factor","cloud native operational audit"] |
Use this skill to inspect an implemented application and produce a structured audit report that downstream quality, security, reporting, and delivery workflows can consume.
pass, partial, fail, or not_applicable.missing evidence explicitly.schemas/audit-report.schema.json when the output is JSON.Use templates/audit-report.md for human-readable reports or the JSON contract in schemas/audit-report.schema.json for machine-readable reports. Every factor finding should include:
Input:
Audit the billing service. Evidence is in package.json, package-lock.json, Dockerfile, helm/, openapi.yaml, .gitea/workflows/test.yml, docs/runbooks/billing.md, and dashboards/billing.json.
Expected output:
Overall status: partial
Pass: codebase, dependencies, port binding, logs
Partial: config, backing services, telemetry, dependency hygiene
Fail: build/release/run separation, supply-chain provenance
Remediation: split release metadata from image build; add SBOM/provenance evidence; document backing-service attachment contracts.