Audit Launcher Subagent — Security agent for Claude Code
Subagent that runs scripts/audit-launcher.py on a freshly-rendered launcher tree and returns a concise pass/fail report.
How to install Audit Launcher Subagent
Installs to ~/.claude/agents/connected-mate-corporate-launcher-audit-launcher-subagent.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Connected-Mate/corporate-launcher/HEAD/agents/audit-launcher-subagent.md -o ~/.claude/agents/connected-mate-corporate-launcher-audit-launcher-subagent.md Restart Claude Code, or start a new session, for it to be picked up.
What Audit Launcher Subagent does
name: audit-launcher description: Subagent that runs scripts/audit-launcher.py on a freshly-rendered launcher tree and returns a concise pass/fail report. Use when Phase 3.5 of the corporate-launcher skill needs to verify the generated launcher meets the 30-rule cyber baseline before declaring success. context: fork tools: Bash, Read, Glob
Audit Launcher Subagent
Runs the corporate-launcher self-audit against a rendered launcher tree and returns a tight pass/fail verdict to the paren
Alternatives in Security
- Beads Warden — Guard the beads execution record: enforce the write-flush-verify discipline that defeats the bd rapid-write ra 2.7k ★
- Genblaze Maintainer — The Genblaze Maintainer — autonomous guardian of the Genblaze repo 560 ★
- Offensive Security Engineer — Red-team the verification engine 179 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Compliance Docx Subagent
Subagent that generates the corporate compliance Word document for RSSI/CISO/DPO review, summarizing the launc
Audit Verification
Independently verifies READY_FOR_VERIFICATION audit tickets and writes PASS/PARTIAL/FAIL verdicts through audi
Dev QA
Quality assurance master. Issues formal verdicts — PASS / CONCERNS / FAIL / WAIVED. Use for story reviews, QA
Checker Summarizer
Runs a given checker CLI command and returns a compact, structured verdict — never the raw output. Use for det
Token Analytics
Use to audit the design-token side of the system: drift between the token source and built outputs (stale / mi
Link Rot Scanner
Read-only audit of the repo's docs for dead links: internal relative links, intra-page anchors, cross-tree ref
Related Skills
Headsign
A tiny phase gate for coding agents: your shell checks decide pass/fail (never the LLM), your workflow routes
Bos Gate
Run the current phase's gate check and report pass/fail per condition
NeXgen Engine
One Git repo to configure every AI CLI — AGENTS.md, MCP, skills, memory rendered to each tool's native format,