A final checking procedure that runs the project's type checks, code-style checks, and tests, then compares the results with the original success criteria.

Use it after changing code to run the configured checks, add or update tests when needed, and report real verification results.

It prevents claiming that code works without actual test results and catches failures before delivery.

06-verify — Cursor rule for coding agents by AG-Dmitry: A final checking procedure that runs the project's type…

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 rules/ag-dmitry/composer-enhanced/06-verify

Clone the repo

git clone --depth 1 https://github.com/AG-Dmitry/composer-enhanced

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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/ag-dmitry/composer-enhanced/06-verify.svg)](https://agentmods.dev/rules/ag-dmitry/composer-enhanced/06-verify)

Your own site

<a href="https://agentmods.dev/rules/ag-dmitry/composer-enhanced/06-verify"><img src="https://agentmods.dev/badge/rules/ag-dmitry/composer-enhanced/06-verify.svg" alt="Measured on agentmods" height="20"></a>

Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 466 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.

Model	Per session	Once invoked
Fable 5	$0.00027	$0.00466
Opus 5	$0.00014	$0.00233
Sonnet 5	$0.00005	$0.00093
Haiku 4.5	$0.00003	$0.00047

Measured 3d ago against content hash 0e5a6ce3436b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

06-verify 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.

agent-protocols/06-verify.mdc · 58 lines

What it actually says

Phase 6 — Verify (Hard Gate)

Persona: Verifier. You trust nothing that has not been run. Fabricated or assumed results ("this should pass") are the single most damaging cheap-model behavior and are strictly forbidden here.

Steps

Run the gates. See project-adapter.mdc for the exact commands configured for this project. Run the structured verifier or the raw gates directly:

# structured verifier (auto-detects package manager):
npx tsx .cursor/rules/agent-protocols/scripts/verify.ts

# or run the raw gates manually as configured in project-adapter.mdc

Paste the real output (or its decisive summary lines) into the chat. Never describe a result you did not actually observe.
Add or update tests when you added or changed behavior. New behavior with no test does not pass this gate. A bug you fixed should get a regression test where practical.
Re-check success criteria from phase 1, one by one, against actual observed behavior — not against your intentions.

On failure

Any failing gate (or unmet success criterion) means the task is not done. Go to 07-reflect-retry.mdc. Do not loosen a test, delete an assertion, or suppress a type error to make the gate pass — that is gaming the gate, which is forbidden.

On pass

Only when every gate passes with shown evidence, fill templates/self-report.md and present it. The self-report + this evidence is what lets you tell the user the task is done.

Working memory

Append the gate results to the Iteration log.

Exit criteria

All gates ran and passed, with pasted evidence.
Tests cover new/changed behavior.
Each success criterion confirmed against real behavior.
Self-report filled.

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.

3d ago First seen · 58 lines · 27 tokens per session scan A 0e5a6ce3436b

Subscribe to this mod's changes

06-verify is a cursor rule published in the GitHub repository AG-Dmitry/composer-enhanced (3 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 466 once invoked, about $0.0001 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.

Testing

06-verify

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Phase 6 — Verify (Hard Gate)

Steps

On failure

On pass

Working memory

Exit criteria

What this file has done since we first saw it

Other cursor rules, from other repositories

angular-20

dev-standard

cli-error-handling

prefer-direct-imports-over-module-mocks

control-plane-descriptors

family-instance-domain-actions