URL Purge Subagent — Development agent for Claude Code
Subagent that scans a rendered launcher for leaked vendor URLs (api.anthropic.com, api.openai.com, etc.) outside the explicit deny lists.
How to install URL Purge Subagent
Installs to ~/.claude/agents/connected-mate-corporate-launcher-url-purge-subagent.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Connected-Mate/corporate-launcher/HEAD/agents/url-purge-subagent.md -o ~/.claude/agents/connected-mate-corporate-launcher-url-purge-subagent.md Restart Claude Code, or start a new session, for it to be picked up.
What URL Purge Subagent does
name: url-purge description: Subagent that scans a rendered launcher for leaked vendor URLs (api.anthropic.com, api.openai.com, etc.) outside the explicit deny lists. Use when Phase 3.6 needs defense-in-depth verification. context: fork tools: Bash, Read, Edit
url-purge subagent
Defense-in-depth verifier for Phase 3.6 of the corporate-launcher pipeline. Runs **after** `render.py` has emitted a launcher tree, and **before** packaging. Parent agent invokes this subagent whenever an ext
Alternatives in Development
- Launcher Scheduler Expert 5.7k ★
- Codex Orchestrator — CLI tool for delegating tasks to GPT Codex agents via tmux sessions 263 ★
- Agentic Workflow Patterns — by ThibautMelen - A comprehensive and well-documented collection of agentic patterns from Anthropic docs, with 204 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Opensource Sanitizer
Pre-public-push safety net. Scans a diff or working tree for leaked secrets, PII, internal references, interna
Submission Runner
In an attended session, submit only exact application packages freshly confirmed by the user, then capture con
Competitor
Role-plays a fictional rival's reaction to the proposal, framed as leaked competitive intelligence — outside-i
Doc Scout
Fetches official platform or vendor documentation for one load-bearing claim, as numbered facts with URLs.
Architrave.Agent
Use to build or change a repository end-to-end through a durable, outcome-driven Run. A thin config-first cond
Permission Analyst
Recommends allow/deny permission rules from denial telemetry and policy via PromptWise. Use to reduce permissi
Related Skills
Claude Guardrails
Hardened security configuration for Claude Code; permission deny rules, shell hooks, and prompt injection defe
StackRadar
StackRadar: free local dev dashboard + network firewall. Find every repo, run command & open port, catch leake
Defense In Depth
Implement multi-layered testing and security best practices.
