sondera-coding-agent-hooks — security grade SAFE, quality 70/100

Security audit verdict: SAFE · quality 70/100

Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by sondera-ai · Agent Tool · ★ 225

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

🔒 Is sondera-coding-agent-hooks safe to install? View the security audit →

About sondera-coding-agent-hooks

Coding Agent Hooks by Sondera Released as part of the Hooking Coding Agents with the Cedar Policy Language talk at Unprompted 2026. A reference monitor for AI coding agents. Rust hook binaries and Cedar policies intercept every shell command, file operation, and web request to forbid exfiltration and destructive behaviors, and enforce information flow control. YARA signatures and Cedar policy evaluation are deterministic; the optional LLM-based classifiers (data sensitivity, secure code policy) are probabilistic. Works with Claude Code, Cursor, GitHub Copilot, and Gemini CLI. Getting Started Prerequisites Install Rust and Cargo using rustup: The YARA signature engine and Cedar policies work without any external dependencies. The LLM-based classifiers (data sensitivity and secure code policy) require Ollama with the model: bash Install Ollama — see https://ollama.com/download for other platforms brew install ollama Pull the model (12 GB) ollama pull gpt-oss-safeguard

Quick Facts

Stars225
Forks32
LanguageRust
CategoryAgent Tool
LicenseMIT
Quality Score70.11159016061/100
Open Issues4
Last Updated2026-09-22
Created2026-02-27
Platformsclaude-code, gemini, rust
Est. Tokens~24k

Compatible Skills

These tools work well together with sondera-coding-agent-hooks for enhanced workflows:

  • agent-swarm — semantic(0.18)+complementary+similar_pop+shared_platform (46%)

sondera-coding-agent-hooks alternative? Top 6 similar tools

Looking for a sondera-coding-agent-hooks alternative? If you're comparing sondera-coding-agent-hooks 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.

  • awesome-android-agent-skills by new-silvermoon · ⭐ 917

    A collection of standardized Agent Skills to teach GitHub Copilot, Claude, Gemini and Cursor about modern Andr

  • claude-code-skill-factory by alirezarezvani · ⭐ 869

    Claude Code Skill Factory — A powerful open-source toolkit for building and deploying production-ready Claude

  • agent-skills by hashicorp · ⭐ 860

    A collection of Agent skills and Claude Code plugins for HashiCorp products.

  • claude-plugins by Kamalnrf · ⭐ 563

    Lightweight registry to discover, install, and manage all public Claude plugins and agent skills for your favo

  • tutor-skills by RoundTable02 · ⭐ 400

    A Claude Code skill that turns PDFs, docs, and codebases into Obsidian study vaults

  • repren by jlevy · ⭐ 374

    Power rename/refactor tool for CLI and agent use

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is sondera-coding-agent-hooks?

sondera-coding-agent-hooks is Hooking implementations and supporting tools for various coding agents (Claude, Cursor, Gemini, etc). It is categorized as a Agent Tool with 225 GitHub stars.

What programming language is sondera-coding-agent-hooks written in?

sondera-coding-agent-hooks is primarily written in Rust.

How do I install or use sondera-coding-agent-hooks?

You can find installation instructions and usage details in the sondera-coding-agent-hooks GitHub repository at github.com/sondera-ai/sondera-coding-agent-hooks. The project has 225 stars and 32 forks, indicating an active community.

What license does sondera-coding-agent-hooks use?

sondera-coding-agent-hooks is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to sondera-coding-agent-hooks?

The top alternatives to sondera-coding-agent-hooks on Agent Skills Hub include awesome-android-agent-skills, claude-code-skill-factory, agent-skills. 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