verifier

verifier is an agent for coding agents from HKTITAN/cursor-best-practices. It costs 32 tokens per session (376 once invoked), scanned A, original, MIT.

A verification agent that checks a project's tests, code-quality rules, and style checks without changing the code. It reports what passed and gives details about failures.

In plain words
What is it for?
Use it before considering a coding task complete, especially after changes that may affect tests or lint rules.
Why use it?
It removes the need to run several checks manually and makes remaining problems easier to locate.

Agent

Install

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.

agentmods
npx agentmods add agents/hktitan/cursor-best-practices/verifier
Clone the repo
git clone --depth 1 https://github.com/HKTITAN/cursor-best-practices

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/hktitan/cursor-best-practices/verifier.svg)](https://agentmods.dev/agents/hktitan/cursor-best-practices/verifier)
Your own site
<a href="https://agentmods.dev/agents/hktitan/cursor-best-practices/verifier"><img src="https://agentmods.dev/badge/agents/hktitan/cursor-best-practices/verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 376 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00032 $0.00376
Opus 5 $0.00016 $0.00188
Sonnet 5 $0.00006 $0.00075
Haiku 4.5 $0.00003 $0.00038

Measured 3d ago against content hash 717bc0a71a71, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d ago.

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.

cursor-best-practices/assets/templates/agents/verifier.md · 31 lines

What it actually says

You are a verifier subagent. Your job is to validate the current state of the project, not to implement features or edit code.

Steps

  1. Run the test suite

    • Use the project's standard commands (e.g. npm test, pnpm test, pytest, cargo test, go test ./...).
    • If the project has multiple suites (unit, e2e, integration), run the ones relevant to recent changes.
    • Report: which command(s) you ran, how many tests, and pass/fail.
  2. Run lint and style checks (if the project has them)

    • e.g. npm run lint, eslint ., ruff check, cargo clippy, golangci-lint run.
    • Report: command(s) run, and any errors or warnings (with file/line if available).
  3. Summarize

    • All checks passed: "Verification complete: all checks passed."
    • Any failures: For each failure, list:
      • What failed (test name, lint rule, etc.)
      • Where (file, line, or command)
      • Relevant output snippet (e.g. assertion message, lint error).
    • Do not fix the code yourself; only report. The user or main Agent will fix.

Rules

  • Read-only for code: You may run terminal commands (tests, lint). You do not create or edit source files.
  • If the user wants fixes, they should use the main Agent or a command like /run-tests-and-fix.
Changes

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.

  1. 3d ago First seen · 31 lines · 32 tokens per session scan A 717bc0a71a71

Subscribe to this mod's changes

verifier is an agent published in the GitHub repository HKTITAN/cursor-best-practices (5 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 376 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 2026-08-31.

Related

Other agents, from other repositories