Menu
Configures Manager and review prompt modes. Explicit user invocation only.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Optimizes text/docs for LLM token efficiency. Triggers - optimize, reduce tokens, compress, deep compress.
Optimizes text, prompts, and documentation for LLM token efficiency. Applies 52 research-backed rules across 8 categories: Claude behavior, token efficiency, structure, deduplication, reference integrity, perception, LLM comprehension, and aggressive lossy (deep only). Use when optimizing prompts, reducing tokens, compressing verbose docs, or improving LLM instruction quality.
Generator: deploys a file-based Kanban into ANY repo via multi-agent analysis, with an optional gated CLAUDE.md-optimization pass. Triggers: init task board, scaffold kanban, set up task tracker, generate task board, optimize CLAUDE.md, добавь канбан-доску, разверни трекер задач.
Interactive guide and tutorial for brewcode plugin suite. Triggers - guide, tutorial, getting started, learn brewcode.
Creates and improves Codex subagents. Triggers: create agent, improve agent, scaffold agent, fix agent.
Extracts etalon classes, patterns, architecture into convention docs. Triggers: extract conventions, etalon classes.
| name | manager |
| description | Configures Manager and review prompt modes. Explicit user invocation only. |
This skill configures ambient prompt guidance only. It does not create, claim, or enforce a hard security wall.
Resolve status, on, off, level, edit, or reset, then choose project state at .codex/brewtools/manager/state.json or personal prompt overrides under ~/.codex/manager/. Obtain confirmation before global writes.
++m: manager guidance, using the plan-aware reference in plan mode.++a: architecture-first guidance.++rr: anti-regression review guidance.++r: two-pass review guidance.on / off: enable or disable ambient prompt state only.level: set balanced or strict prompt wording; it does not change sandbox or authorization.edit / reset: update or remove prompt overrides after showing the diff.status: show hook registration, state source, level, override paths, and the no-security-wall limitation.The plugin uses SessionStart and UserPromptSubmit hooks. Preserve unrelated hook entries and review changed definitions with /hooks.