verification-gate

verification-gate is a cursor rule for Cursor from fmflurry/settings-opencode. It costs 1,029 tokens per session, scanned A, original, MIT.

A verification rule that requires an agent to identify the project type and run the relevant checks before reporting code as finished. It prevents a successful-sounding response when the build or tests are still failing.

In plain words
What is it for?
Use it at the end of coding tasks to check the project build, tests, type checks, or other applicable validation before declaring the work complete.
Why use it?
It makes completion claims depend on actual project verification rather than on whether the edits were written.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc). Also seen: mentions subagents.

Good fit Use it at the end of coding tasks to check the project build, tests, type checks, or other applicable validation before declaring the work complete.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/fmflurry/settings-opencode/verification-gate
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.

Clone the repo
git clone --depth 1 https://github.com/fmflurry/settings-opencode

Made for: Cursor.

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 verification-gate

README.md
[![agentmods](https://agentmods.dev/badge/rules/fmflurry/settings-opencode/verification-gate/github.svg)](https://agentmods.dev/rules/fmflurry/settings-opencode/verification-gate)
Your own site
<a href="https://agentmods.dev/rules/fmflurry/settings-opencode/verification-gate"><img src="https://agentmods.dev/badge/rules/fmflurry/settings-opencode/verification-gate/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for verification-gate

Your own site · 80×15
<a href="https://agentmods.dev/rules/fmflurry/settings-opencode/verification-gate"><img src="https://agentmods.dev/badge/rules/fmflurry/settings-opencode/verification-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,029 This file is loaded in full into every session.
When invoked 1,029 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01029 $0.01029
Opus 5.5 $0.00412 $0.00412
Sonnet 5.5 $0.00206 $0.00206
Haiku 4.5 $0.00103 $0.00103

Measured 8d ago against content hash 593ddf59c6f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verification-gate 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 8d 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.

plugins/fmflurry-harness/rules/verification-gate.mdc · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verification Gate (mandatory before "done")

Agents have repeatedly reported "implementation done" while the build is red. This rule fixes that. Applies to anyone who wrote or edited source code in the current turn — main agent or subagent.

Hard rule

You MAY NOT tell the user "done", "complete", "ready", "ready to merge", or render a green-status final message until you have:

  1. Detected the project type from manifests present in cwd (search recursively, not only at root — .csproj, pom.xml, build.gradle*, etc. often live in subdirs):
    • angular.json / tsconfig.json / package.json → TS/Angular
    • Cargo.toml → Rust
    • go.mod → Go
    • pyproject.toml (with mypy/pyright config) → Python
    • pom.xml → Java/Maven
    • build.gradle / build.gradle.kts → Java or Kotlin/Gradle (check settings.gradle* + presence of *.kt vs *.java to disambiguate; Kotlin Multiplatform falls under Kotlin)
    • *.sln / *.slnx / *.slnf / *.csproj / *.fsproj / *.vbproj / global.json / Directory.Build.props → .NET (C#/F#/VB). .slnx is the XML-based format (default in .NET 10 SDK, supported since 9.0.200); .slnf is a solution filter referencing a .sln/.slnx
  2. Run the matching independent verification yourself (do not trust a subagent's self-report):
    • TS/Angular: npx tsc --noEmit --pretty false
    • Rust: cargo check --message-format=short
    • Go: go build ./...
    • Python: mypy . or pyright
    • Java/Maven: mvn -q -DskipTests compile (multi-module: run from repo root, Maven recurses)
    • Java/Gradle: ./gradlew --offline compileJava compileTestJava -x test (or compileKotlin for Kotlin)
    • .NET: dotnet build --nologo -clp:ErrorsOnly --no-restore (run dotnet restore first if obj/ is missing); pass the explicit path for a solution: dotnet build path/to/Solution.sln or dotnet build path/to/Solution.slnx (SDK 9.0.200+ required for .slnx)
  3. When a scripts.lint entry exists in package.json, run <pm> run lint (auto-detect package manager: bun.lock/bun.lockb → bun; pnpm-lock.yaml → pnpm; yarn.lock → yarn; else npm). Lint errors are blocking — treat them exactly like build errors: fix before claiming "done".
  4. When the diff changes behavior, also run the tests covering the changed files (e.g. dotnet test --filter <Class>, npx vitest related <files> --run, npx jest --findRelatedTests <files>) or use the run skill for UI changes; a compile proves nothing about behavior.
  5. Paste the last ~15 lines of each command's actual output into your reply, OR explicitly state n/a — <reason>. No paraphrasing.

Read the full file on GitHub · 49 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. 8d ago First seen · 49 lines · 1,029 tokens per session scan A 593ddf59c6f8

Subscribe to this mod's changes

verification-gate is a cursor rule published in the GitHub repository fmflurry/settings-opencode (171 stars, last pushed yesterday), licensed MIT. It adds 1,029 tokens to every session, about $0.0041 per session on Opus 5.5. 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 2026-10-08.