A unified pipeline for efficient and effective coding agents.
One tool, no config — works the moment it lands.
Many great packages make coding agents more effective and efficient — but discovering, installing, updating, and unifying them is painful, especially for non-technical users. The best tools exist; the wiring is the real cost.
tokless — the lazy one-command solution.
| ✔️ | Best packages, unified — picks the most effective, efficient tools and wires them without conflicts |
| ✔️ | One command, done — pick your agent, restart, go |
| ✔️ | All platforms — macOS, Linux, Windows |
| ✔️ | Zero config — everything wired, no manual edits |
| ✔️ | Simple updates — tokless update upgrades everything in one shot |
| ✔️ | Non-tech friendly — under 30 seconds, anyone can do it |
macOS / Linux:
curl -fsSL https://raw.githubusercontent.com/HoangP8/tokless/main/scripts/install.sh | bashWindows (PowerShell):
irm https://raw.githubusercontent.com/HoangP8/tokless/main/scripts/install.ps1 | iex
 Claude Code ✓ Done |
 OpenCode ✓ Done |
 Codex ✓ Done |
 Antigravity ✓ Done |
 Pi In progress |
 Cursor In progress |
 Factory Droid CLI In progress |
 GitHub Copilot In progress |
Pick one, some, or all:
tokless # interactive: pick agents
tokless --agents claude,opencode # wire just these
tokless --agents claude,opencode,codex,antigravity # all| Tool | ⭐ | What it does |
|---|---|---|
| karpathy-skills |  |
Distilled meta-rules from Karpathy's LLM-coding post — think before coding, simplicity first, surgical changes, goal-driven. Drops overbuild and wrong-assumption failures. |
| caveman |  |
Skill/plugin forcing terse caveman-speak across 30+ agents — 65% output token cut, technical content untouched. |
| ponytail |  |
Skill embedding a lazy senior dev — minimum-code, stdlib-first, no speculative features across 16 agents. |
| rtk |  |
CLI proxy filtering/compressing command output before it hits the LLM; 100+ commands, single Rust binary, <10ms overhead. |
| codegraph |  |
Pre-indexed SQLite code knowledge graph — auto-syncs on file change, returns verbatim source + call paths via 1 MCP tool across 8+ agents. |
| context-mode |  |
MCP server for 17 clients — sandboxes tool output, persists session memory, enforces think-in-code. |
Each tool is wired into each agent through the agent's native config system — MCP servers, plugin registries, hooks, instruction files (CLAUDE.md / AGENTS.md / GEMINI.md).
| Tool | Claude | OpenCode | Codex | Antigravity |
|---|---|---|---|---|
| rtk | PreToolUse + Allow | Plugin | PreToolUse + PermissionRequest + Trust + Rules | PreToolUse + Allow |
| caveman | Plugin + CLAUDE.md | Plugin + AGENTS.md | Skills + AGENTS.md | Skills + GEMINI.md |
| ponytail | Plugin + CLAUDE.md | Plugin + AGENTS.md | Marketplace + AGENTS.md | Extension + GEMINI.md |
| codegraph | MCP + Allow + CLAUDE.md | MCP + AGENTS.md | MCP + AGENTS.md | PostToolUse + PreInvocation + MCP + Allow + GEMINI.md |
| context-mode | MCP + Allow + CLAUDE.md | Plugin + AGENTS.md | PreToolUse + MCP + AGENTS.md | MCP + Allow + GEMINI.md |
tokless Install + wire everything (default; safe to re-run)
tokless update Show version diff and upgrade tools
tokless doctor Show what's wired; warn about broken bits
tokless index Build per-project codegraph indexes
tokless disable Disable one or more agents
tokless uninstall Remove everything tokless touched
tokless self-update Update the tokless CLI itself
tokless --version Print tokless version
tokless --help Show all commands and flags
Flags:
--agents <list> Subset: claude,opencode,codex,antigravity
--tools <list> Subset: rtk,caveman,ponytail,codegraph,context-mode
--dry-run Preview, no writes
--verbose Every step
--yes Skip confirmations
Restart agents after install so they pick up new config.