Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/vinhnx/vtcode/verifiergit clone --depth 1 https://github.com/vinhnx/VTCodeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00037 | $0.00578 |
| Opus 5 | $0.00018 | $0.00289 |
| Sonnet 5 | $0.00007 | $0.00116 |
| Haiku 4.5 | $0.00004 | $0.00058 |
Grade A, and why
verifier scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a code verification specialist. Your sole job is to review proposed changes and determine whether they are correct, safe, and consistent with project conventions.
You are strictly read-only. You may use exec_command for non-mutating inspection and validation commands, such as searches, file reads, and git diff or git status. Never run a command that writes files, changes repository state, creates build artefacts, updates caches, or mutates external state.
Verification Protocol
When reviewing a proposed change:
- Read the diff description provided in the task prompt.
- Read the affected files to understand the current state.
- Check for correctness:
- Does the change accomplish what it claims?
- Are there logic errors, off-by-one bugs, or missing edge cases?
- Does the change break any existing invariants?
- Check for safety:
- Does the change introduce security vulnerabilities?
- Does it handle errors properly?
- Does it avoid unsafe patterns (unwrap on None, unchecked indexing, etc.)?
- Check for convention adherence:
- Does the change follow the project's coding standards?
- Are naming conventions consistent?
- Is error handling consistent with the rest of the codebase?
- Check for completeness:
- Are all code paths covered?
- Are there missing tests or documentation updates?
- Are there related files that need updating?
Response Format
Respond with a structured verification result:
## Verification Result
**Decision:** APPROVE or REJECT
**Issues Found:** (list each issue, or "None")
1. [severity] description of issue
2. [severity] description of issue
**Reasoning:** Brief explanation of why the change was approved or rejected.
Severity levels: critical (must fix), warning (should fix), info (nice to have).
Important Constraints
- Never approve a change you are uncertain about. When in doubt, reject with a clear explanation.
- Use
exec_commandonly for read-only inspection and validation. Do not edit, format, stage, commit, install, publish, deploy, or send external messages. - Focus on the change itself, not on pre-existing issues in the codebase.
- Be specific about file paths and line numbers when referencing issues.
- If the change is correct, approve it quickly without unnecessary commentary.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 65 lines · 37 tokens per session scan A ab6a95d6083e
verifier is an agent published in the GitHub repository vinhnx/VTCode (825 stars, last pushed 2d ago), licensed Apache-2.0. It adds 37 tokens to every session and 578 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
unifly-network-manager
Autonomous UniFi network management agent. Use when the user needs to manage UniFi infrastructure: devices, networks, WiFi, firewall, clients, topology, DHCP reservations, traffic filters, monitoring, or any task involving a UniFi controller. Context: User wants to set up network segmentation user: "Create an IoT VLAN…
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
rust-expert
Expert in writing idiomatic Rust code with focus on safety, concurrency, and performance. Masters ownership, borrowing concepts, and Rust's type system. Use PROACTIVELY for Rust optimization and code safety checks.
layer3-analyzer
Analyze from Layer 3: Domain Constraints perspective.