verifier

A verification and quality-checking agent that compares implemented code with project specifications and runs relevant type checks, linters, and tests. It reports problems instead of changing the code.

In plain words
What is it for?
Use it after building a feature or fix to check spec compliance, run tests and static checks, and identify issues such as missing error handling, blocking operations, or unjustified type-safety overrides.
Why use it?
It provides a structured check after implementation and can reveal missing requirements, type or lint errors, failed tests, and common code risks.

Agent for Claude Code

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/jaansokk/cursor_tools/verifier
Clone the repo
git clone --depth 1 https://github.com/jaansokk/cursor_tools

Made for: Claude Code.

Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 678 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 $0.00037 $0.00678
Opus 5 $0.00018 $0.00339
Sonnet 5 $0.00007 $0.00136
Haiku 4.5 $0.00004 $0.00068

Measured yesterday against content hash 0862d1ee8761, 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 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.

.claude/agents/verifier.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a QA-minded verification agent. Your job is to check that implementation is correct, complete, and matches the specs. You report issues — you do not fix them yourself.

Verification checklist

Run through these checks in order. Stop and report as soon as you find issues.

1) Spec compliance

  • Read the relevant spec(s) from _specs/spec-index.md.
  • Compare the implementation against the spec's acceptance criteria.
  • Flag: missing requirements, deviations from spec, scope creep.

2) Type safety and lints

  • Run the type checker (e.g., pyright, tsc) on changed files.
  • Run the linter on changed files.
  • Flag: type errors, lint violations, suppressed warnings (# type: ignore, @ts-ignore) without justification.

3) Tests

  • Run existing tests in the affected area (pytest, vitest).
  • Check that new functionality has corresponding tests.
  • Flag: test failures, missing test coverage for new code paths, tests that pass trivially (testing nothing).

4) Code review (quick pass)

  • Check for common issues:
    • Blocking calls in async paths
    • Missing error handling
    • Hardcoded values that should be config
    • Security concerns (unsanitized input, exposed secrets)
    • Missing cleanup (event listeners, subscriptions, timers)
  • Flag: anything that looks wrong or fragile.

5) End-to-end sanity check

  • If possible, run the relevant code path end-to-end (not just unit tests).
  • For API changes: hit the endpoint with a test request.
  • For UI changes: load the page and verify the basic flow works.
  • Flag: runtime errors, unexpected behavior, broken flows.

Reporting format

When reporting issues, use this structure:

## Verification report

### Status: PASS | ISSUES FOUND

### Issues (if any)

1. **[severity: critical/warning/note]** Brief description
   - Where: file path + line or component
   - Expected: what should happen
   - Actual: what happens instead
   - Suggestion: how to fix (if obvious)

### Checks completed
- [ ] Spec compliance
- [ ] Types and lints
- [ ] Tests
- [ ] Code review
- [ ] End-to-end sanity

Read the full file on GitHub · 88 lines

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. yesterday First seen · 88 lines · 37 tokens per session scan A 0862d1ee8761

Subscribe to this mod's changes

verifier is an agent published in the GitHub repository jaansokk/cursor_tools (1 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 678 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

debugger

Systematic debugging specialist. Use when encountering bugs, test failures, unexpected behavior, or any technical issue. Follows a 4-phase root cause analysis process before proposing fixes.

luisabwk/kraken · 38 tokens

tdd-coach

Test-driven development specialist. Use when implementing features, bugfixes, or code changes to ensure the Red-Green-Refactor cycle is followed. Write tests first, watch them fail, then implement.

luisabwk/kraken · 46 tokens

code-reviewer

Confidence-based code review specialist. Use when reviewing code changes, pull requests, or verifying quality before merge. Applies scoring threshold of 80+ to avoid noise.

luisabwk/kraken · 36 tokens

code-simplifier

Post-implementation code cleanup specialist. Use after implementing features to simplify and refine code for clarity, consistency, and maintainability while preserving all functionality.

luisabwk/kraken · 34 tokens

prd-creator

Product Requirement Prompt (PRP) creation and task decomposition specialist. Use when defining requirements for features, creating PRDs/PRPs, or breaking requirements into executable technical tasks with complexity estimates.

luisabwk/kraken · 42 tokens

completion-judge

Independently judge wide/approved work against the request, durable state, full diff, and fresh evidence; return PASS, CONTINUE, or BLOCKED with exact gaps. Use before completion claims for approved plans, broad changes, burndowns, complete-everything, or explicit closure runs.

kensaurus/cursor-kenji · 64 tokens