epistemic-self-monitoring
This plugin enforces epistemic discipline in Claude Code by separating observations from conjectures, requiring claims to carry their evidence and a named falsifier before they become facts or closures. It installs five hooks at UserPromptSubmit, PostToolUse, Stop, SessionEnd, and SubagentStop to nudge the agent toward verification, with a non-blocking default mode and optional strict mode that gates closures on complete [EPISTEMIC CLOSE] blocks.
Install
Source: https://github.com/3dgiordano/agent-plugins/tree/HEAD/plugins/epistemic-self-monitoring
What it's made of
1 skill · 5 hooks
- Commands
- 0
- Agents
- 0
- Skills
- 1
- MCP servers
- 0
- Hooks
- 5 · PostToolUse, 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).