minimax-m3-verification

minimax-m3-verification is a cursor rule for Cursor from madebyaris/advance-minimax-m3-cursor-rules. It costs 26 tokens per session (853 once invoked), scanned A, original, MIT.

A verification rulebook for checking software changes with evidence. It covers choosing suitable checks, reproducing bugs before fixing them, and inspecting visual or multimodal results directly.

In plain words
What is it for?
Use it to choose verification steps for runtime behavior, interaction, styling, navigation, persistence, integrations, and promised tools such as Tailwind, routing, or storage.
Why use it?
It prevents unsupported claims by matching each claim to proof, such as a red-then-green test for a bug fix or direct inspection for a styling change.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it to choose verification steps for runtime behavior, interaction, styling, navigation, persistence, integrations, and promised tools such as Tailwind, routing, or storage.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/madebyaris/advance-minimax-m3-cursor-rules/minimax-m3-verification
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/madebyaris/advance-minimax-m3-cursor-rules

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 minimax-m3-verification

README.md
[![agentmods](https://agentmods.dev/badge/rules/madebyaris/advance-minimax-m3-cursor-rules/minimax-m3-verification/github.svg)](https://agentmods.dev/rules/madebyaris/advance-minimax-m3-cursor-rules/minimax-m3-verification)
Your own site
<a href="https://agentmods.dev/rules/madebyaris/advance-minimax-m3-cursor-rules/minimax-m3-verification"><img src="https://agentmods.dev/badge/rules/madebyaris/advance-minimax-m3-cursor-rules/minimax-m3-verification/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 minimax-m3-verification

Your own site · 80×15
<a href="https://agentmods.dev/rules/madebyaris/advance-minimax-m3-cursor-rules/minimax-m3-verification"><img src="https://agentmods.dev/badge/rules/madebyaris/advance-minimax-m3-cursor-rules/minimax-m3-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 853 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00026 $0.00853
Opus 5 $0.00013 $0.00426
Sonnet 5 $0.00005 $0.00171
Haiku 4.5 $0.00003 $0.00085

Measured 11d ago against content hash 78e51aca8905, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

minimax-m3-verification 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 11d 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/minimax-m3-verification.mdc · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

M3 Verification Playbook

Extends the always-on minimax-m3-status-verification contract with check selection, shell/browser guidance, multimodal-grounded checks, and self-review. The status labels, minimum proof table, and closeout shape live in that always-on rule — do not restate them here.

Proof Selection

  • Match the proof to the claim being made.
  • Prefer the smallest proof that can honestly support the user-facing claim.
  • Strengthen the proof when the claim involves runtime behavior, interaction, styling, navigation, persistence, or integration.
  • If the deliverable promises a styling or toolchain layer (Tailwind, shadcn, routing, persistence), verify that layer directly — do not assume the scaffold wired it correctly.
  • Visual / design / styling claim → multimodal-grounded: read the attached image/frame, name the file path, name the region inspected, and check the relevant region. Do not infer from prose or from a memory of the pre-change state. See the minimax-m3-multimodal-input skill for the full workflow.
  • Bug fix → red → green: reproduce the failure with an exact check before fixing, then re-run that same check after. A check that was never red proves the wrong thing.

Test Integrity During Verification

A passing check only counts as proof if the check itself was not bent:

  • Never delete, skip, loosen, widen tolerances on, or special-case a test to reach green. If the test looks wrong, present the evidence to the user — changing the spec is their call.
  • A new test must be able to fail: confirm it fails against the pre-fix code (or would, by construction) before counting it as proof.
  • Hardcoding the expected output into production code, or branching on test-only inputs, is claim-gaming — treat the work as blocked, not verified.

Shell-Based Checks

Use the smallest useful command first. Prefer the repo's own scripts and CI entrypoints when they exist (see core Code Discipline).

  • JavaScript/TypeScript: lint, typecheck, build, targeted tests, focused scripts
  • Python: ruff, targeted pytest, import or compile checks
  • Go: go build, go test, go vet
  • Rust: cargo check, cargo test, cargo clippy
  • Flutter: flutter analyze, flutter test
  • Swift: swift build, swift test, xcodebuild when applicable

Read the full file on GitHub · 77 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. 11d ago First seen · 77 lines · 26 tokens per session scan A 78e51aca8905

Subscribe to this mod's changes

minimax-m3-verification is a cursor rule published in the GitHub repository madebyaris/advance-minimax-m3-cursor-rules (125 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 853 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 2026-08-30.