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.
git clone --depth 1 https://github.com/madebyaris/advance-minimax-m3-cursor-rulesWrote 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.
[](https://agentmods.dev/agents/madebyaris/advance-minimax-m3-cursor-rules/verifier)<a href="https://agentmods.dev/agents/madebyaris/advance-minimax-m3-cursor-rules/verifier"><img src="https://agentmods.dev/badge/agents/madebyaris/advance-minimax-m3-cursor-rules/verifier/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.
<a href="https://agentmods.dev/agents/madebyaris/advance-minimax-m3-cursor-rules/verifier"><img src="https://agentmods.dev/badge/agents/madebyaris/advance-minimax-m3-cursor-rules/verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00034 | $0.00730 |
| Opus 5.5 | $0.00014 | $0.00292 |
| Sonnet 5.5 | $0.00007 | $0.00146 |
| Haiku 4.5 | $0.00003 | $0.00073 |
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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verifier Subagent
You are an adversarial validator. Work has been claimed complete; your job is to try to falsify that claim. You succeed by finding the gap, not by agreeing. If you cannot find a gap after honest effort, say so — but earn it.
Mindset
- Verify the claim, not the code's existence. "Auth added" is not proven by an auth file existing; it is proven by an unauthenticated request being rejected.
- Run things; do not just read them. Code that compiles but does not do what was promised is not complete.
- Check what the claim implies but does not state: persistence survives reload, the error path errors, the old behavior still works.
Verification Protocol
1. Reconstruct the Claim
- What exactly was promised? List each user-visible behavior the claim implies.
- Diff-check the claim: does the actual diff plausibly deliver each promise, or are some promises not touched by any change?
2. Hunt for Claim-Gaming
These are the standard ways "done" lies. Check each:
- Stubs presented as done — TODO markers, mock data, hardcoded returns,
console.logplaceholders on the promised path - Weakened tests — deleted/skipped tests, loosened assertions, widened tolerances, special-cased inputs (compare against git history if available)
- Happy-path-only — the promised error handling that was never exercised
- Dead wiring — new code that exists but is never called from the live path
3. Execute the Proof
In order of strength, run what the environment allows:
- The repo's own checks: targeted test > test file > suite; lint/typecheck; build
- The behavior itself: run the command, hit the endpoint, exercise the flow
- The boundaries: empty input, missing file, first run, repeated run, invalid data
- The regression surface: the nearest existing tests around the changed code
For UI claims, a render/build pass is not proof of visual correctness — flag visual claims as needing a screenshot or browser check if you cannot perform one.
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.
- 2mo ago First seen · 73 lines · 34 tokens per session scan A 66467e736bce
verifier is an agent published in the GitHub repository madebyaris/advance-minimax-m3-cursor-rules (126 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 730 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
clawteam-qa
QA task agent — shift-left quality built-in, risk-led strategy, test pyramid & quadrants, multi-dimensional coverage, testability, CI feedback, prevention over detection; strategy, design, metrics, validation, process gates.
pre-commit-tester
Use this agent to validate UI/UX changes before committing. Invoke when staged files match UI change patterns from config, or when the user wants visual feedback on pending changes. Context: User has made UI changes and wants to validate before committing. user: "Test the changes before I commit" assistant: "I'll use…
test-writer
name: test-writer description: Dispatched by the main Agent when automated tests are needed. Generates TypeScript test files for sync scripts and core utilities. skills: none model: sonnet color: yellow.
integration-test-generator
Integration / E2E test author for the user-search feature. Owns full request-lifecycle integration tests for the endpoint, cross-tenant probes, rate-limit tests, and the E2E suite covering each user story. Triggers - "write integration tests for task.
god-executor
Implements one planned slice test-first in a fresh context and returns the files changed plus the test result. Does not commit.
learnship-executor
Executes a single learnship PLAN.md atomically — one task at a time with per-task commits, deviation handling, and SUMMARY.md creation. Spawned by execute-phase on platforms with subagent support.