hautc-it/cil

Claude Intelligence Layer — token-efficient context runtime for Claude Code. Persistent memory (SQLite FTS5), structured workflows (/develop /review /commit /wrap-up), output compression, and MCP integration.

1Stars on the repository

32Mods indexed here, across every type

1mo agoLast push, which is what freshness is scored on

MITLicence, which decides whether bodies are shown

Sort Relevance Recently updated Fewest tokens Security grade Repo stars Stars this week Top rated 5 mods

implementer

01

Agent

Role: Bounded execution of well-defined implementation tasks.

1 1mo ago A 0 tokens original MIT

planner

02

Agent

Role: Task decomposition and sequenced implementation planning.

1 1mo ago A 0 tokens original MIT

researcher

03

Agent

Role: Understand existing code, APIs, and architecture before implementation.

1 1mo ago A 0 tokens original MIT

reviewer

04

Agent

Role: Validate implementation correctness and catch issues before they ship.

1 1mo ago A 0 tokens original MIT

debugger

05

Agent Claude Code

Use for systematic investigation of bugs, test failures, or runtime errors. Reproduces first, then forms 2-3 ranked hypotheses with evidence, investigates code paths and git history, and proposes the minimal fix. Never guesses; never shotgun-debugs. Returns a single report — does not modify code.

1 1mo ago A 64 tokens original MIT

2 more from hautc-it/cil →