Is the Agent Verifier (Verification) skill free?

Yes. The skill itself is free from Aurite-ai/agent-verifier. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Agent Verifier (Verification) SkillProof Score?

9.2/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.

How do I install Agent Verifier (Verification)?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Agent Verifier (Verification) with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Agent Verifier (Verification)

Orchestrated security/pattern/quality/language audit for AI agent code, with pattern-vs-heuristic tagging.

by Aurite-ai · Aurite-ai/agent-verifier

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 9.2/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · c2394b5

Fed it a planted agent.py (hardcoded sk-live key, a system prompt promising a nonexistent `execute_sql` tool); it caught both exactly per its own report template, but also flagged a while-True loop purely for lacking a literal `break` keyword even though a `return` inside it does exit cleanly — the pattern check is stricter than the actual bug it's hunting.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 4/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 5/5

What Agent Verifier (Verification) does

Runs four sub-skills (security, agent patterns, quality, language) against agent code and merges them into one tagged report distinguishing [P] mechanical pattern matches from [H] judgment calls — covering hardcoded secrets, unbounded loops, missing retry limits, and hallucinated tool references. Triggers on 'verify agent', 'verify my agent', or 'audit agent'; the four sub-skills must be installed alongside the orchestrator or its steps 2-5 have nothing to load.

How to install Agent Verifier (Verification)

git clone https://github.com/Aurite-ai/agent-verifier
cd agent-verifier
mkdir -p ~/.claude/skills
cp -r skills/verification ~/.claude/skills/verification

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Agent Verifier (Verification)

/verification Orchestrated security/pattern/quality/language audit for AI agent code, with pattern-vs-heuristic tagging.

It also activates on plain-language prompts like these:

Verify my agent's code for security and quality issues
Run a full verification audit on this agent codebase
Audit this AI agent for hardcoded secrets and hallucinated tools

Frequently asked questions

Is the Agent Verifier (Verification) skill free?: Yes. The skill itself is free from Aurite-ai/agent-verifier. SkillProof publishes the install command and an independent test verdict at no cost.
Does Agent Verifier (Verification) work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Works with setup. Fed it a planted agent.py (hardcoded sk-live key, a system prompt promising a nonexistent `execute_sql` tool); it caught both exactly per its own report template, but also flagged a while-True loop purely for lacking a literal `break` keyword even though a `return` inside it does exit cleanly — the pattern check is stricter than the actual bug it's hunting.
What is the Agent Verifier (Verification) SkillProof Score?: 9.2/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
How do I install Agent Verifier (Verification)?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Agent Verifier (Verification) with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.