Skill Claude CodeCodex
The essential habits for an AI agent with memory — session bookends, learning triggers, verification, safety, and the operational discipline that turns raw recall into compounding intelligence. Pinned, always-injected.
41 tagged discipline, measured the same way as everything else here.
Skill Claude CodeCodex
The essential habits for an AI agent with memory — session bookends, learning triggers, verification, safety, and the operational discipline that turns raw recall into compounding intelligence. Pinned, always-injected.
Plugin Claude Code
Rules your coding agent physically cannot ignore. A Claude Code plugin (and LLM-agnostic rule pack) that stops reactive patching, guessed citations, surface-level fixes and premature "done" claims by intercepting the agent's own tool calls — PreToolUse denies the edit before it lands, and a nine-layer Stop gate…
Agent
A read-only checking agent that compares stated facts or file references with the actual source files. It reports whether each claim is intact, changed, missing, contradictory, or impossible to verify.
Command
A command that prints checklists for reviewing work before editing, after editing, during verification, and when synchronizing changes across a codebase. It can print all checklists or one selected checklist.
Command
A command that checks translated rule and prompt files against their English source files. It verifies matching files, heading structure, and required command tokens in enforcement lines.
Command
A command-line tool for managing a project’s sync-gate configuration, which checks whether related files are updated together. The configuration can define file patterns that require matching updates elsewhere.
Hook
Runs when a session starts, executing inject_context.py via python with --event. From skymanbp/cc-enforcer.
Hook
Runs when you submit a prompt, before the agent sees it, executing inject_context.py via python with --event. From skymanbp/cc-enforcer.
Hook
Runs before the agent uses a tool for Read, Edit, Write and Bash tool calls, executing read_guard.py and bash_guard.py via python (2 commands). From skymanbp/cc-enforcer.
Skill Claude CodeCodex
A repository-wide scan for stale, outdated, duplicated, incorrect, or drifting documentation and code. It checks whether written instructions still match the current project.
Skill Claude CodeCodex
A structured debugging process for investigating bugs, errors, failed tests, and unexpected behavior. It starts by creating a quick, repeatable way to reproduce the problem before testing possible causes.
At most 3 mods per repository are shown here — the rest are on their repository pages: