Weekly Task Prompt — Security agent for Claude Code
Weekly GTM audit: flags tags/triggers/variables/containers that won't fire, with fixes and root-cause reasoning.
How to install Weekly Task Prompt
Installs to ~/.claude/agents/anishdagdu-gtm-health-agent-weekly-task-prompt.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/anishdagdu/gtm-health-agent/HEAD/agents/weekly-task-prompt.md -o ~/.claude/agents/anishdagdu-gtm-health-agent-weekly-task-prompt.md Restart Claude Code, or start a new session, for it to be picked up.
What Weekly Task Prompt does
name: gtm-weekly-health-agent description: Weekly GTM audit: flags tags/triggers/variables/containers that won't fire, with fixes and root-cause reasoning
You are the GTM Health Agent, acting for a VP of Analytics Marketing. Run a READ-ONLY audit of Google Tag Manager using the GTM MCP connector tools (gtm_auth_status, gtm_account, gtm_container, gtm_workspace, gtm_tag, gtm_trigger, gtm_variable, gtm_built_in_variable, gtm_version_header, gtm_version, gtm_user_permission). Never create,
Alternatives in Security
- Patina Fidelity Auditor — Triggers to audit whether a patina rewrite preserved meaning versus the original text 352 ★
- Dotnet Code Review Agent — WHEN reviewing code for correctness, performance, security, and architecture concerns 76 ★
- Release Auditor — Pre-release audit for a single plugin in the monorepo — takes a plugin slug and cross-references plugin.json v 72 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Rc Opus
Reasoning-heavy work handed up from a session on a weaker model — architecture and design decisions, root-caus
Scout Opus High
Read-only analyst for judging inside the sub-agent — root-cause analysis, a security sweep, reviewing a diff f
Tier Opus
Subagent for a tier/opus issue — unclear root cause, cross-cutting refactors, concurrency/data-loss/security r
AI Redteam
Use PROACTIVELY for AI CTF challenges and LLM security challenges. Triggers on prompt injection, jailbreak, LL
Risk Qa.Agent
Use when completed changes need functional verification, regression risk assessment, code review, test suffici
Vzt Oracle
Frontier debugging agent (Fable 5.1) — root-cause analysis for impossible bugs: race conditions, heisenbugs, c
Related Skills
Mkt Gtm
Google Tag Manager expert — tag configurations, triggers, variables, data layer schema, and implementation spe
Secondmate Reason
Ask a read-only reasoning model (via secondmate) a hard analysis question — root-cause, triage, plan review, p
Personal Claude Assistant Template
Give Claude Code a memory that learns. Every session boots knowing who you are; your work gets journaled, corr