follow-through
follow-through enforces guardrails on Claude Code agent behavior through hooks that block incomplete announcements, prose questions, unsubstantiated claims on unverified screens, and other risky patterns, while enabling parallel sessions to coordinate through a shared registry and freshness checks. It requires no API keys or external services, works in any repository with no setup, and provides configurable gates for destructive commands and language-specific prose validation.
Install
Source: https://github.com/YasMax91/groundwork/tree/HEAD/follow-through
What it's made of
1 skill · 6 hooks
- Commands
- 0
- Agents
- 0
- Skills
- 1
- MCP servers
- 0
- Hooks
- 6 · PostToolUse, PreToolUse, SessionEnd, SessionStart, Stop, UserPromptSubmit
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
python3- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (YasMax91).