by prapaa-ai
Terminal-native AI coding assistant for real repositories. Inspect code, edit files, run tests, and verify changes from the CLI.
Requires a passing catalog security scan. Resolve the flagged issues and resubmit to enable featuring.
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
# Add to your Claude Code skills
git clone https://github.com/prapaa-ai/agavGuides for using ai agents skills like agav.
Last scanned: 9/13/2026
{
"issues": [
{
"type": "npm-audit",
"message": "@vitest/coverage-v8: Vulnerability found",
"severity": "critical"
},
{
"type": "npm-audit",
"message": "@vitest/mocker: Vitest: Path Traversal / Arbitrary File Read via @vitest/mocker Redirect Mock",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "esbuild: esbuild enables any website to send any requests to the development server and read the response",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "vite: Vite Vulnerable to Path Traversal in Optimized Deps `.map` Handling",
"severity": "high"
},
{
"type": "npm-audit",
"message": "vite-node: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "vitest: Vulnerability found",
"severity": "critical"
},
{
"file": "README.md",
"line": 32,
"type": "remote-install",
"message": "Install command (remote install script piped to a shell — review the source before running): \"curl -fsSL https://agav.dev/install.sh | bash\"",
"severity": "low"
}
],
"status": "FAILED",
"scannedAt": "2026-09-13T09:00:37.629Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how agav compares with popular alternatives.
Terminal-native autonomous agent for real repositories and projects
⚠️ Experimental Beta — Agav is under active development. Expect breaking changes, rough edges, and rapid iteration. Feedback and bug reports are welcome!
No Node.js required. One command, self-contained binary:
curl -fsSL https://agav.dev/install.sh | bash
Windows PowerShell:
irm https://www.agav.dev/install.ps1 | iex
Windows Command Prompt:
curl -fsSL https://agav.dev/install.cmd -o install.cmd
install.cmd
del install.cmd
Download binaries or pre-releases from Releases. See docs.agav.dev/getting-started/installation for detailed installation steps.
agav
Pick a provider and model, or use defaults:
agav --provider openai --model gpt-4o
agav --provider openrouter --model openrouter/auto
agav --provider ollama --model llama3.2
Non-interactive for scripts and CI:
agav run "review the code in src/"
agav -P "what does this project do?"
cat error.log | agav -P "explain this error"
Keep it current:
agav update
Today, the most powerful AI tools are controlled by a handful of companies. They choose which models you use, where your data goes, and how much you pay. If they change the rules tomorrow, you have no choice but to follow.
We’re building the alternative, an AI that works for you, runs on your terms, and belongs to no one.
You own it. Apache 2.0 open source. No lock-in, no hidden telemetry, auditable code.
You choose the brain. 7 providers — Anthropic, OpenAI, OpenRouter, NVIDIA NIM, Gemini, Vertex AI, Ollama. Switch models mid-session with /model, run local with Ollama, or route via OpenRouter.
You control the data. Encrypted API keys, local-first option, per-tool permissions, and sandboxed commands on macOS/Linux.
Autonomous and verifiable. Plans are created and tracked automatically, human-in-the-loop for destructive actions, and non-interactive agav run for CI with JSON Schema output.
/model. Fast /fast and deep /deep shortcuts.agav run and agav --print with per-tool permissions and optional JSON Schema output./compact reclaims context without losing plans./undo, and planning UI.Email: contact@agav.dev
Discord: discord.gg/6u3m2JN6k
Documentation source lives in docs/. To run locally: cd docs && npm install && npm run dev.
agav is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by prapaa-ai. Terminal-native AI coding assistant for real repositories. Inspect code, edit files, run tests, and verify changes from the CLI. It has 136 GitHub stars.
agav failed SkillsLLM's automated security scan, which flagged one or more high-severity issues. Review the Security Report section carefully before using it.
Clone the repository with "git clone https://github.com/prapaa-ai/agav" and add it to your Claude Code skills directory (see the Installation section above).
agav is primarily written in TypeScript. It is open-source under prapaa-ai on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh agav against similar tools.
No comments yet. Be the first to share your thoughts!