change-quality-gate

change-quality-gate is a cursor rule for Cursor from granoflow/granoflow-mcp-server. It costs 305 tokens per session, scanned A, original, MIT.

Quality rules for reviewing changes according to their type, such as documentation, scripts, or TypeScript tools. They describe suitable checks and reject tests that only repeat prose from a document.

In plain words
What is it for?
They help choose files to edit, run the project's checks, test scripts and MCP tools, and assess when agent evaluations are appropriate.
Why use it?
They make reviews proportional to the change and avoid spending effort on tests that do not verify behavior. They also provide a consistent quality gate before changes are accepted.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit They help choose files to edit, run the project's checks, test scripts and MCP tools, and assess when agent evaluations are appropriate.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/granoflow/granoflow-mcp-server/change-quality-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/granoflow/granoflow-mcp-server

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 change-quality-gate

README.md
[![agentmods](https://agentmods.dev/badge/rules/granoflow/granoflow-mcp-server/change-quality-gate.svg)](https://agentmods.dev/rules/granoflow/granoflow-mcp-server/change-quality-gate)
Your own site
<a href="https://agentmods.dev/rules/granoflow/granoflow-mcp-server/change-quality-gate"><img src="https://agentmods.dev/badge/rules/granoflow/granoflow-mcp-server/change-quality-gate.svg" alt="Measured on agentmods" height="20"></a>
Per session 305 This file is loaded in full into every session.
When invoked 305 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 $0.00305 $0.00305
Opus 5 $0.00152 $0.00152
Sonnet 5 $0.00061 $0.00061
Haiku 4.5 $0.00030 $0.00030

Measured 7d ago against content hash 3e5fe3dbedb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

change-quality-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 7d 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/rules/change-quality-gate.mdc · 30 lines

What it actually says

Change Quality Gate

Prefer conventional engineering checks over ritual “natural-language Excel” test tables. Do not invent tests that only freeze wording.

By change type

Change Quality bar
Skill / reference prose (roles, policy, workflow copy) List files + intent → edit → npm run check. No toContain on markdown. Optional human skim.
Skill scripts / lint helpers Real I/O + exit codes under tests/python/ (or project equivalent).
TypeScript / MCP tool behavior Vitest (or project suite): ok, codes, schema, structured fields — not skill body phrases.
Agent follows long skill text LLM evals if/when the repo has them — not required in CI today.

Forbidden

  • Fake acceptance matrices that only restate documentation sentences.
  • Locking SKILL.md / references/** prose with snapshot/toContain tests (see skill-testing.mdc).

Still do

  • Analyze and confirm approach before large edits when the user wants planning.
  • Name files to touch and the outcome for each todo.
  • For behavioral code: prefer tests that exercise real inputs/outputs; run the gate after edits; use timeouts and non-interactive flags.
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. 7d ago First seen · 30 lines · 305 tokens per session scan A 3e5fe3dbedb9

Subscribe to this mod's changes

change-quality-gate is a cursor rule published in the GitHub repository granoflow/granoflow-mcp-server (0 stars, last pushed 1mo ago), licensed MIT. It adds 305 tokens to every session, about $0.0015 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.