No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by vincentkoc · Codex Skill · ★ 519
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is tokenjuice safe to install? View the security audit →
tokenjuice 🧃 lean output compaction for terminal-heavy agent workflows. what it does an agent or harness calls noisy tools like , , , , or . tokenjuice sits in front of that tool call, runs it, trims the fat from the output, and passes back a much cleaner result to the harness. the important bit is the boundary: the original command still runs tokenjuice compacts the observed output after execution / gives you an explicit unaltered escape hatch when you need it raw output can be stored locally when you explicitly ask for it the harness gets a smaller, more useful payload instead of a wall of terminal junk install then: why tool output wastes absurd amounts of context. your llm needs a diet. tokenjuice compacts observed output after execution, gives hosts a boring, deterministic summary by default, and only stores raw output when you explicitly ask for it. goals library first, not framework-locked JSON rules for parseability and inspection explicit and modes file-backed artifacts that a
| Stars | 519 |
| Forks | 51 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 71.5936742445923/100 |
| Last Updated | 2026-09-08 |
| Created | 2026-04-14 |
| Platforms | cli, node |
| Est. Tokens | ~15k |
These tools work well together with tokenjuice for enhanced workflows:
Looking for a tokenjuice alternative? If you're comparing tokenjuice with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder Rerank, Multi-Sc
Command Your AI Agent Empire from the CEO Desk — A local-first AI agent office simulator that orchestrates CLI
A personal 24x7 AI assistant like OpenClaw that runs on your messaging platforms. Send a message on WhatsApp,
A complete security skill suite for OpenClaw, Hermes, PicoClaw and NanoClaw agents (and variants). Protect you
An open-source AI marketing operating system for strategy, SEO, AEO/GEO, paid media, content, CRM, and analyti
OpenClaw plugin implementing the A2A (Agent-to-Agent) protocol v0.3.0 — bidirectional agent communication gate
Explore other popular codex skill tools:
tokenjuice is 🧃 Token weight loss. Lean output compaction for terminal-heavy agent workflows. Works as a native CLI tool or as an extension to popular coding and agent frameworks.. It is categorized as a Codex Skill with 519 GitHub stars.
tokenjuice is primarily written in TypeScript. It covers topics such as openclaw-plugin, optimization, token.
You can find installation instructions and usage details in the tokenjuice GitHub repository at github.com/vincentkoc/tokenjuice. The project has 519 stars and 51 forks, indicating an active community.
tokenjuice is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to tokenjuice on Agent Skills Hub include memory-lancedb-pro, claw-empire, secure-openclaw. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: