tokf — security grade SAFE, quality 73/100

Security audit verdict: SAFE · quality 73/100

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 mpecan · Agent Tool · ★ 196

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is tokf safe to install? View the security audit →

About tokf

tokf tokf.net — reduce LLM context consumption from CLI commands by 60–90%. Commands like , , and produce verbose output packed with progress bars, compile noise, and boilerplate. tokf intercepts that output, applies a TOML filter, and emits only what matters — so your AI agent sees a clean signal instead of hundreds of wasted tokens. Before / After — 61 lines → 1 line: Without tokf With tokf

ai-toolsclaude-codeclicommand-linecontext-windowdeveloper-toolshomebrewllmoutput-filterrust

Quick Facts

Stars196
Forks19
LanguageRust
CategoryAgent Tool
LicenseMIT
Quality Score73.1963541943805/100
Open Issues5
Last Updated2026-09-06
Created2026-02-18
Platformsclaude-code, cli, rust
Est. Tokens~34k

Compatible Skills

These tools work well together with tokf for enhanced workflows:

  • toktrack — semantic(0.19)+complementary+same_lang+similar_pop+shared_platform (52%)
  • bridle — semantic(0.16)+complementary+same_lang+similar_pop+shared_platform (50%)
  • claude-warden — semantic(0.15)+complementary+rare_topics+similar_pop+shared_platform (50%)

tokf alternative? Top 6 similar tools

Looking for a tokf alternative? If you're comparing tokf with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • omni by fajarhide · ⭐ 371

    Your agent pays twice for output it has already seen. OMNI returns a handle instead: 97.2% off a file read twi

  • rlm-rs by zircote · ⭐ 55

    Rust CLI implementing the Recursive Language Model (RLM) pattern for Claude Code. Process documents 100x large

  • homebrew-pandafilter by AssafWoo · ⭐ 100

    The context intelligence layer for AI coding agents. Compressing noise, routing content to the right strategy,

  • claude-brain by memvid · ⭐ 576

    Give Claude Code photographic memory in ONE portable file. No database, no SQLite, no ChromaDB - just a single

  • gptree by travisvn · ⭐ 290

    A CLI tool to provide LLM context for coding projects by combining project files into a single text file (or c

  • claude-code-statusline by rz1989s · ⭐ 477

    Transform your Claude Code terminal with atomic precision statusline. Features flexible layouts, real-time cos

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is tokf?

tokf is Config-driven CLI tool that compresses command output before it reaches an LLM context. It is categorized as a Agent Tool with 196 GitHub stars.

What programming language is tokf written in?

tokf is primarily written in Rust. It covers topics such as ai-tools, claude-code, cli.

How do I install or use tokf?

You can find installation instructions and usage details in the tokf GitHub repository at github.com/mpecan/tokf. The project has 196 stars and 19 forks, indicating an active community.

What license does tokf use?

tokf is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to tokf?

The top alternatives to tokf on Agent Skills Hub include omni, rlm-rs, homebrew-pandafilter. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Agent Tool tools