Back to directory

cc-rig

cc-rig generates a Claude Code project setup - CLAUDE.md, hooks, agents, skills, commands and plugins tuned to a chosen framework - and then reports over time how much cache discipline it is actually saving.

cc-rig

cc-rig asks a small set of questions about a project's framework and working style, then writes a tuned set of native Claude Code configuration files (thirty to sixty-five of them) instead of leaving a project with just a bare CLAUDE.md. Nothing it generates is proprietary; removing cc-rig later leaves a working configuration behind.

Beyond initial setup, cc-rig reads a project's local Claude Code session logs to produce ongoing reports: a savings report showing cache-related cost trends over time, an audit that scores session discipline against the project's configuration tier, a drift report comparing the project to a fresh generation, and a weekly retro combining all three with one suggestion.

It is a Python CLI, keeps its state on the local machine, and is released under the MIT license.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.