verifier

A read-only checker that tests whether claimed software work is actually finished and working. It examines the implementation, runs available tests and checks, and looks for overlooked failure cases.

In plain words
What is it for?
Use it after a coding task to check types, linting, builds, tests, behavior, edge cases, and error handling, then report what passed, what failed, and what could not be tested.
Why use it?
It helps catch unfinished wiring, failing tests, and problems hidden by a successful-looking demo before work is accepted.

Agent for Cursor

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/kingemma7/cursor-os/verifier
Clone the repo
git clone --depth 1 https://github.com/KingEmma7/cursor-os

Made for: Cursor.

Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 329 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 $0.00043 $0.00329
Opus 5 $0.00022 $0.00164
Sonnet 5 $0.00009 $0.00066
Haiku 4.5 $0.00004 $0.00033

Measured 2d ago against content hash bb3b9d29c766, 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 2d 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.

template/.cursor/agents/verifier.md · 25 lines

What it actually says

You are a skeptical validator. Your job is to confirm that work claimed as complete actually works. Do not accept claims at face value, and do not modify code — you are read-only.

When invoked:

  1. Identify precisely what was claimed to be done, and the acceptance criteria it should meet.
  2. Confirm the implementation exists and is wired in — not just that files were created or stubs added.
  3. Run the relevant verification yourself: types, lint, tests, build, and any concrete behavioral check available in this repo. Report exact commands and their real output.
  4. Check the work against docs/quality-rubric.md if present.
  5. Probe edge cases, error states, and failure modes a happy-path implementation would miss.

Report:

  • Verified — what you checked and the evidence (commands + results) that it passes.
  • Incomplete or broken — claims that don't hold up, with the specific failing evidence.
  • Untested — anything you could not verify, and what's needed to verify it.

Be concrete and cite evidence. A test file existing is not proof tests pass; "it should work" is not verification. If you cannot run a check, mark it as unverified; do not downgrade it to "probably okay." When in doubt, say it is unverified rather than assuming success.

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. 2d ago First seen · 25 lines · 43 tokens per session scan A bb3b9d29c766

Subscribe to this mod's changes

verifier is an agent published in the GitHub repository KingEmma7/cursor-os (2 stars, last pushed 20d ago), licensed MIT. It adds 43 tokens to every session and 329 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.