agf — security grade SAFE, quality 71/100

Security audit verdict: SAFE · quality 71/100

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 subinium · Codex Skill · ★ 152

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

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

About agf

agf Find the AI coding session you meant to resume. is a local-first fuzzy finder for AI coding-agent sessions. Search local sessions across Claude Code, Codex, Gemini CLI, Cursor CLI, OpenCode, Kiro, pi, and Hermes — then resume the right one in a keystroke. Install Requires a Rust toolchain ( recommended). Prebuilt binaries for macOS, Linux, and Windows are also available on the Releases page. Quick Resume (no TUI) Why agf? AI coding agents are great at keeping context — until you lose the terminal. You switch projects, close a tab, forget the session ID, or resume the wrong agent. Then you either dig through history files or start over. gives you one searchable list of local agent sessions and resumes the right one. Supported agents reads the session files each agen

agentic-workflowai-agentsai-codingclaude-codeclicodexdeveloper-toolsfuzzy-searchgemini-cligrok-build

Quick Facts

Stars152
Forks19
LanguageRust
CategoryCodex Skill
LicenseMIT
Quality Score70.6409227723437/100
Open Issues4
Last Updated2026-09-19
Created2026-02-17
Platformsclaude-code, cli, codex, gemini, rust
Est. Tokens~24k

Compatible Skills

These tools work well together with agf for enhanced workflows:

  • forge-orchestrator — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (57%)
  • bridle — semantic(0.34)+complementary+same_lang+similar_pop+shared_platform (57%)
  • mcp_agent_mail_rust — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (56%)
  • template-repo — semantic(0.15)+complementary+same_lang+similar_pop+shared_platform (55%)

agf alternative? Top 6 similar tools

Looking for a agf alternative? If you're comparing agf 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.

  • pixtuoid by IvanWng97 · ⭐ 483

    Terminal pixel-art office for AI coding agents

  • toktrack by mag123c · ⭐ 190

    Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)

  • claude-code-rust by srothgan · ⭐ 197

    A native Rust terminal interface for Claude Code

  • terminal-jarvis by BA-CalderonMorales · ⭐ 131

    In the midst of all the tools out there that you can possibly use to keep track of them. Here's a "shovel" tha

  • agenttrace by luoyuctl · ⭐ 131

    Local-first Rust TUI/CLI for auditing AI coding-agent sessions: cost, tokens, latency, failures, and health|本地

  • cc9s by kincoy · ⭐ 69

    A k9s-inspired CLI and TUI for managing Claude Code sessions — browse, search, inspect, and clean up your AI c

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is agf?

agf is Find, search, and resume AI coding-agent sessions across Claude Code, Codex, Grok Build, Kimi Code, Qwen Code, Gemini, Cursor, and more.. It is categorized as a Codex Skill with 152 GitHub stars.

What programming language is agf written in?

agf is primarily written in Rust. It covers topics such as agentic-workflow, ai-agents, ai-coding.

How do I install or use agf?

You can find installation instructions and usage details in the agf GitHub repository at github.com/subinium/agf. The project has 152 stars and 19 forks, indicating an active community.

What license does agf use?

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

What are the best alternatives to agf?

The top alternatives to agf on Agent Skills Hub include pixtuoid, toktrack, claude-code-rust. 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 Codex Skill tools