A skill file for removing AI tells from prose
Repository Index
47,133 repositories indexed
1–8 of 8 · Most stars
TranslatedA multi-platform Hook + Skill Guard for AI coding agents in Codex/GPT workflows: stop unrequested hashes, checksums, and task-scope creep.
HERO = Hashing · Edge cases · Rubrics · Overbuild — the four shapes coding agents over-defend in. A paste-in contract that stops them. Works with Claude Code, Codex, Antigravity, Cursor, Copilot, Windsurf, Gemini CLI.
- agents-md
- ai-agents
- claude-code
- claude-md
Stop paying the multimodal tax. Your AI agent keeps every image it has seen but only sends the ones it needs: lighter chats, no endless reconnecting, no starting over. Works with Codex, Claude Code, Cline, Gemini CLI, OpenCode, WorkBuddy and more. Install once, forget it.
- codex
- codex-plugin
- context-management
- developer-tools
Give the agent a machine. Just not yours. Each AI coding agent gets its own isolated machine with root, Docker, and systemd - active defense detects and stops threats automatically.
50x your usage with cheap-ag. Opus/Astra plans, a dirt-cheap model writes every line, and tests decide what ships. Your $20 plan stops hitting limits. One MCP server for Claude Code & Codex.
A local retry shim that stops Codex's "Selected model is at capacity" error from interrupting your work.
See where it leaks, stop paying for it — a live Claude Code status line that prices every turn, your subagents, cache rebuilds, plus limits, context and git.