Use when the user asks about lfg/GrokBuild rules injection, project rules files, matching, or environment configuration.
Scanned 9/8/2026
Install to Claude Code
Skills Directorynpx -y skills add islee23520/lfg --skill rules --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Rules?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/islee23520-rules-lfg)More formats (shields.io, HTML) on the badges page.
---
name: rules
description: Use when the user asks about lfg/GrokBuild rules injection, project rules files, matching, or environment configuration.
---
# GrokBuild Rules (lfg)
Rules injection is automatic once the lfg Grok plugin is enabled. It injects:
- static project instructions on `SessionStart` and `UserPromptSubmit` (native rules hook + config loader)
- matching file-specific rules after edit-like tools via PostToolUse (rules-injector glue)
Dynamic PostToolUse output is injected as additional context when the host attaches hook output. If hook context is not visible, read matching rule files from disk directly.
Supported project sources:
- `CONTEXT.md`
- `.omo/rules/**/*.md`
- `.claude/rules/**/*.md`
- `.cursor/rules/**/*.md`
- `.github/instructions/**/*.md`
- `.github/copilot-instructions.md`
- Root / nested `AGENTS.md` (fail-closed project awareness)
## Environment (lfg / Grok)
Prefer lfg/Grok-owned knobs when present. Codex-only `CODEX_RULES_*` names may appear in upstream OMO docs as historical reference; on GrokBuild do not require `CODEX_HOME` or Codex plugin layout.
## Cross-host note
Upstream may brand this as "Codex Rules". On GrokBuild the owner is **lfg native rules** (`lfg-native-rules.mjs` + `src/core/omo/rules-engine`).
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling
