Claude Code mod

zetetic-insights

The learning loop: every main turn is kept in a ledger across sessions (phase, effort, steps, failed tool calls, agents, advisor calls), joined with the outcomes observed at tool.call (commits kept or reverted, test exits, PR verdicts and merges, no transcript) and the ones /insights writes, and the project's goals; probe sessions are counted and kept out; a phase whose evidence, read on the rung each run had and with Wilson intervals, says so gets its tool-loop effort moved one notch (every applied move is measured pre/post on the same phase, the same task classes and the steps its ceiling decided), written to a calibration file the autopilot reads. /calibrate apply, /calibrate reset. Starts in observe: proposals are shown, not applied.

Workflow mods Plugin marketplace Source

Install

Inside Claude Code
/plugin marketplace add cdeust/claude-mods
/plugin install zetetic-insights@claude-mods

Mods install like plugins. Run /reload-plugins or start a new session to load it.

What it can access

Reach
Unknown
Sees
classic hooks, every tool call, subagent spawns
Hooks
classic.SessionEndsession.endsession.startclassic.SessionStartturn.completetool.callprompt.composeagent.spawncommand.run

From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.

How Claude Code mods work

  • A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
  • It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
  • Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
  • Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Claude Code docs

Details

Folder
mods/zetetic-insights
Marketplace
claude-mods
Author
cdeust
Last updated
25 October 2026

FAQ

What is zetetic-insights?

The learning loop: every main turn is kept in a ledger across sessions (phase, effort, steps, failed tool calls, agents, advisor calls), joined with the outcomes observed at tool.call (commits kept or reverted, test exits, PR verdicts and merges, no transcript) and the ones /insights writes, and the project's goals; probe sessions are counted and kept out; a phase whose evidence, read on the rung each run had and with Wilson intervals, says so gets its tool-loop effort moved one notch (every applied move is measured pre/post on the same phase, the same task classes and the steps its ceiling decided), written to a calibration file the autopilot reads. /calibrate apply, /calibrate reset. Starts in observe: proposals are shown, not applied. It is a mod for Claude Code, from cdeust/claude-mods on GitHub.

What can the zetetic-insights mod access?

Its reach could not be worked out from its code. It sees classic hooks, every tool call, subagent spawns. Like any mod, it runs with your permissions.

How do I install zetetic-insights?

Inside Claude Code (v2.1.287 or later), run /plugin marketplace add cdeust/claude-mods and then /plugin install zetetic-insights@claude-mods.

More workflow mods

Browse the most popular Claude Code mods, all workflow mods, or the skills and MCP server directories.