A governance layer for Claude Code sessions: hooks that check an agent's commands before they run, a spec-first workflow, and project memory the next session reads.
This repository also configures its own agents. See what code-conductor tells them →
Skill Claude CodeCodex
Rules for when and how to spawn sub-agents: Explore for 3+ file reads, parallel agents for independent tasks, summaries only — raw output never enters main context.
Skill Claude CodeCodex
Always-active simplicity rules: no speculative abstractions, one job per function, max 30 lines, flat over nested with early returns, descriptive names, comments explain why.
Skill Claude CodeCodex
4-phase adversarial review protocol: pre-flight analysis, adversarial execution check, self-correction loop, and [VALIDATION] report.
Skill Claude CodeCodex
Lookup chain enforced before any file read or search: project and global memory, grep/glob, targeted read — stop at the first step that answers.
Skill Claude Code
Response verbosity protocol: reads the level from /.claude/memory/verbosity.md and applies the MIN, INFO or VERBOSE output rules to every reply.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: