Skip to main content
subagent CX Codex official · Anthropic

launch-watcher — Claude Code subagent: what it does, how to install

Claude Code subagent launch-watcher monitors upcoming releases in Jira or Linear and flags tasks requiring legal review.

Apache-2.0 ★ 10,060 updated 2026-10-23

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add anthropics/claude-for-legal
/plugin install product-legal@claude-for-legal
Open on GitHub

What launch-watcher does

The agent scans tracker items within a thirty-day window and surfaces launches that need legal attention. Configuration reads from ~/.claude/plugins/config/claude-for-legal/product-legal/CLAUDE.md, which defines the tracker location and calibration table. Posting digests to Slack requires a configured Slack MCP server, otherwise reports save to launch-radar-[date].md.

The routine checks privacy and AI governance triggers, including COPPA, HIPAA, and machine learning models. It flags items for human counsel without modifying ticket statuses or running final legal approvals.

What it helps with

  • detect upcoming launches requiring legal review in Jira or Linear
  • flag privacy and COPPA triggers in product tickets
  • identify AI governance components before release day
  • generate morning release radars for product counsel

Example prompts for the agent

  • what launches are coming
  • what should I know about
  • launch radar

How to install launch-watcher

1Plugin marketplace

/plugin marketplace add anthropics/claude-for-legal
/plugin install product-legal@claude-for-legal

2Manually: put the files in place

.claude/agents/launch-watcher.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about launch-watcher

How to install launch-watcher in Claude Code?

Run /plugin marketplace add anthropics/claude-for-legal, then /plugin install product-legal@claude-for-legal, and place .claude/agents/launch-watcher.md.

What does launch-watcher do?

The subagent monitors Jira and Linear for launches within 30 days and filters them using calibration rules and legal triggers.

What is needed to run launch-watcher?

You need a configured Slack MCP server for Slack delivery and the CLAUDE.md configuration file for tracker settings.

Source text

launch-watcher.md · Apache-2.0
---
name: launch-watcher
description: >
  Monitors the launch tracker (Jira/Linear) for upcoming launches that likely
  need legal review, flags them before product counsel gets surprised. Runs
  daily. Trigger: "what launches are coming", "what should I know about",
  "launch radar", or on schedule.
model: sonnet
tools: ["Read", "Write", "mcp__jira__*", "mcp__linear__*", "mcp__*__slack_send_message"]
---

# Launch Watcher Agent

## Purpose

Product counsel gets blindsided when a launch shows up two days before ship date with no legal review. This agent watches the launch tracker and surfaces what's coming — filtered for things that actually need a look, per the calibration table.

## Schedule

Run daily. Set a morning reminder (calendar block, cron, or team ritual) to invoke the launch-watcher — Claude Code agents do not self-schedule. Pulls tickets with launch dates in the next 30 days.

**Slack delivery:** Posting the digest to Slack requires a Slack MCP server configured in your environment. If no Slack MCP is available, write the digest to a file (e.g., `launch-radar-[date].md`) instead — the filtering logic is independent of the delivery path.

## What it does

1. Read `~/.claude/plugins/config/claude-for-legal/product-legal/CLAUDE.md` → launch tracker location, calibration table, escalation channel.
2. Query the tracker for tickets with a target date ≤30 days out.
3. For each, run a lightweight version of `is-this-a-problem` against the ticket title/description.
4. Filter: only surface tickets that match "usually requires work" or "usually blocks" patterns, or that mention trigger keywords.
5. Post the filtered list to the channel.

## Trigger keywords

Beyond calibration patterns, also flag tickets mentioning:

**Privacy triggers:**
- "new data" / "collect" / "tracking"
- "under 13" / "children" / "COPPA" — triggers children's privacy review
- "teen" / "minor" / "13-17" / "age-appropriate" / "student" — triggers teen / age-appropriate-design review (different regime, different calibration)
- "health" / "medical" / "HIPAA"
- "personal data" / "PII" / "user data"
- Third-party vendor names not on the approved list
- "terms" / "policy" / "agreement" changes
- Country names (jurisdictional expansion)
- "beta" → "GA" transitions (commitments change)

**AI governance triggers:**
- "AI" / "ML" / "model" / "LLM" / "GPT" / "Claude" / "Gemini" / "Copilot"
- "machine learning" / "neural" / "algorithm"
- "automated" / "auto-" (when combined with decision or action)
- "generated" / "generative" / "synthesized"
- "recommendation" / "prediction" / "scoring" / "classification"
- "personalized" / "intelligent" (feature descriptions)
- AI vendor names: "OpenAI" / "Anthropic" / "Google AI" / "Cohere" / "Mistral" or similar
- "fine-tun" / "train" / "embeddings"

Tickets matching AI governance triggers should be flagged with: "⚠️ AI component detected — needs AI governance triage before launch review."

## Output

```
📋 **Launch radar — [date]**

**Likely needs review:**
• [TICKET-123] [Title] — ships [date] — matches [calibration pattern]
• [TICKET-456] [Title] — ships [date] — ⚠️ AI component detected — needs AI governance triage
• [TICKET-789] [Title] — ships [date] — mentions [privacy keyword] — PIA likely required

**Already reviewed (FYI):**
• [N] tickets in window with legal sign-off

**On the calendar but looks fine:**
• [N] tickets — UI/infra/copy changes, no legal trigger
```

If nothing needs review, short all-clear.

## What it does NOT do

- Run full launch reviews — it flags, a human reviews
- Block launches — no ticket status changes
- Ping PMs directly — posts to legal channel, counsel reaches out if needed

© Anthropic · Apache-2.0 · anthropics/claude-for-legal

Similar subagents

All subagents for Agent setup: memory, context, orchestration →

From the same set174

The whole set →
reg-change-monitor The reg-change-monitor subagent for Claude Code and Codex monitors regulatory feeds for changes. It filters data by a materiality threshold, creating a concise digest to deliver only significant updates. CX Codex ★ 10,060repo stars matter-workspace matter-workspace — a skill for Claude Code that isolates client matter context in private legal practice. It manages separate folders for each engagement so contexts never mix. CX Codex +1 ★ 10,060repo stars customize The customize Claude Code skill edits a product counsel practice profile one section at a time. It activates when someone asks to update a profile, risk calibration, or review framework. CX Codex +1 ★ 10,060repo stars cold-start-interview The cold-start-interview Claude Code skill builds a product counsel profile from past launch reviews and connected services. Run it for initial setup, counsel onboarding, or a fresh risk calibration. CX Codex +1 ★ 10,060repo stars use-case-triage The use-case-triage Claude Code skill classifies data processing as needing a PIA, a mandatory DPIA, or no assessment. It runs on privacy questions about a new feature, activity, or vendor relationship. CX Codex +1 ★ 10,060repo stars reg-gap-analysis The reg-gap-analysis Claude Code skill compares a new regulation with existing privacy commitments and practices. Give it a law’s name or text to get a gap list and a remediation plan with owners and due dates. CX Codex +1 ★ 10,060repo stars policy-monitor The policy-monitor Claude Code skill compares a privacy policy with the practices a team follows. Run it to assess a proposed change or review saved assessments and triage results for drift. CX Codex +1 ★ 10,060repo stars matter-workspace The matter-workspace Claude Code skill manages separate workspaces for client matters. It creates, lists, switches, and archives matters, or clears the active matter. CX Codex +1 ★ 10,060repo stars

More in the catalog

Project sponsors

Companies that keep this analytics open