Audit Collector — Security agent for Claude Code
Read-only subagent that runs an audit skill (default /audit-setup) and returns a compact severity-bucketed finding summary.
How to install Audit Collector
Installs to ~/.claude/agents/a2ngerer-claude_onboarding_agent-audit-collector.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/a2ngerer/claude_onboarding_agent/HEAD/.claude/agents/audit-collector.md -o ~/.claude/agents/a2ngerer-claude_onboarding_agent-audit-collector.md Restart Claude Code, or start a new session, for it to be picked up.
What Audit Collector does
name: audit-collector description: Read-only subagent that runs an audit skill (default `/audit-setup`) and returns a compact severity-bucketed finding summary. Wraps the audit skill; never writes files. tools: Bash, Glob, Grep, Read model: sonnet
Audit Collector
Role
Invoke an audit skill (by default `audit-setup`) and summarize its findings into a severity-bucketed report. The collector exists so the orchestrator can receive a one-screen summary instead of the full audit output
Alternatives in Security
- Finding Reporter — Phase 14 per-finding report authoring agent 125 ★
- Vuln Verifier — Adjudicates a single candidate security finding produced by the vuln-analyst hunter 107 ★
- Audit Agent — Audit worker for spec-driven development spawned by the speq-audit orchestrator 49 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Audit Learning Agent
Analyzes past audit logs, detects patterns, and returns a structured retro for the orchestrator to write. Read
Portfolio Manifest Collector
Read-only inventory collector dispatched by portfolio-audit: gathers each repo's project/portfolio.yml manifes
API Auditor
API security specialist. Launched by the audit orchestrator with assigned coverage units and surface-map hotsp
Iac Auditor
IaC and container security specialist. Launched by the audit orchestrator with assigned coverage units and sur
Checker Summarizer
Runs a given checker CLI command and returns a compact, structured verdict — never the raw output. Use for det
God Security Auditor
Adversarial security reviewer. Walks the OWASP Top 10 against the real code paths, probes where it can, checks
Related Skills
Proof Obligations
Scan the entire Coq project for proof obligations (admit, Admitted, Axiom declarations), classify each by inte
Dsh Auto Review
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns stru
Codemesh
Query the code knowledge graph before reading code. One-call context assembly via codemesh_answer returns inli