← Browse
termination-self-monitoring
3dgiordano ★ 0
This Claude Code plugin enforces discipline around agent termination by catching unfaithful stopping reasons (fatigue, context limits, apologies) and requiring them to be replaced with checkable ones (gate-not-run, owner-choice, budget-spent, limit-observed, or none to continue). It scans final messages via hooks and optionally blocks stops until the agent provides verifiable evidence for the termination.
Install
> /plugin marketplace add 3dgiordano/agent-plugins/tree/HEAD/plugins/termination-self-monitoring
> /plugin install termination-self-monitoring
Source: https://github.com/3dgiordano/agent-plugins/tree/HEAD/plugins/termination-self-monitoring
What it's made of
1 skill · 4 hooks
- Commands
- 0
- Agents
- 0
- Skills
- 1
- MCP servers
- 0
- Hooks
- 4 · SessionEnd, Stop, SubagentStop, UserPromptSubmit
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
node- Talks to
- nothing external detected
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 (3dgiordano).