Self Audit Orchestrator — Security agent for Claude Code
Use this agent at the start of a new 14-day cycle (Day 1), during the cycle to execute the 2-hour sprint, and at the close (Day 14) for system-wide scoring and improvement installation.
How to install Self Audit Orchestrator
Installs to ~/.claude/agents/mgtechgroup-lyra-lynx-mythonexus-self-audit-orchestrator.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/mgtechgroup/lyra-lynx-mythonexus/HEAD/agents/self-audit-orchestrator.md -o ~/.claude/agents/mgtechgroup-lyra-lynx-mythonexus-self-audit-orchestrator.md Restart Claude Code, or start a new session, for it to be picked up.
What Self Audit Orchestrator does
name: self-audit-orchestrator description: Use this agent at the start of a new 14-day cycle (Day 1), during the cycle to execute the 2-hour sprint, and at the close (Day 14) for system-wide scoring and improvement installation. Also invoke when the user asks for "start cycle", "close cycle", "score the system", or "what should we improve". Examples:
Context: New 14-day cycle is starting user: "start a new audit cycle" assistant: "Using self-audit-orchestrator to pick the focus arAlternatives in Security
- Vault Librarian — Run vault maintenance: detect orphan notes, find broken wikilinks, validate frontmatter completeness, flag sta 4.6k ★
- Patina Fidelity Auditor — Triggers to audit whether a patina rewrite preserved meaning versus the original text 352 ★
- Dashclaw Security Reviewer — Read-only security reviewer specialized for the DashClaw stack (Next.js 16 App Router, Neon/Postgres via repos 297 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Governance Learner
Feedback Distiller. Use this agent at sprint close to audit /memory/ logs, distill systemic patterns from bug-
Nosql Paradigm Auditor
Read-only NoSQL paradigm specialist. Use proactively during a database audit of document, key-value, or wide-c
Perf Complexity Analyzer
Invoke second during a performance audit, after perf-pattern-scanner has produced its findings. Given the scan
Vuln Verifier
Adjudicates a single candidate security finding produced by the vuln-analyst hunter. Independently re-reads th
Authoring Loop
ScholarEval-gated authoring improvement loop. Define a subject, author with the matching authoring agent (scop
Principle Auditor P2
Audit a target artifact through P2 (Start with Why) ONLY. Member of an audit- team launched by /audit --team.
Related Skills
GitHub App Persona
Replace a classic PAT with a GitHub App installation token for org-wide automation. Trigger when the user asks
Readability
Repo-wide readability & maintainability improvement (behavior-preserving)
Sdlc Project Init
Bootstrap a greenfield project through a guided interview. Produces .sdlc/steering/product.md and tech.md so c