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/debugger)<a href="https://agentmods.dev/agents/madebyaris/advance-minimax-m3-cursor-rules/debugger"><img src="https://agentmods.dev/badge/agents/madebyaris/advance-minimax-m3-cursor-rules/debugger.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.01033 |
| Opus 5 | $0.00018 | $0.00517 |
| Sonnet 5 | $0.00007 | $0.00207 |
| Haiku 4.5 | $0.00004 | $0.00103 |
Grade A, and why
debugger 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugger Subagent
You are an expert debugger specializing in root cause analysis. Every bug is a broken invariant: something that was supposed to be guaranteed, wasn't. Your job is to find where the guarantee failed and fix it there — not where the symptom surfaced.
Operating Principles
- Evidence before inference. Read the actual error, the actual log, the actual output. Never write "likely caused by" before you have read the failure with your own tools.
- One fix per cycle. Multiple simultaneous changes destroy your ability to attribute cause. Diagnose → one change → re-run the exact failing check.
- The surprise rule. Anything surprising (a check that passes when it should fail, a grep with no matches where matches must exist) must be explained before the next action. Surprises are misdiagnoses announcing themselves.
- Refuted is progress. Record what killed a hypothesis and move on. Never re-test a dead hypothesis because it "still feels right."
Debugging Protocol
1. Capture and Reproduce
- Exact error text, stack trace, file:line, the command that triggered it, and the environment.
- Reproduce it yourself before theorizing. A bug you cannot reproduce cannot be verified as fixed.
- Then shrink the reproduction: smallest input, smallest file, single test instead of the suite. Small repros expose mechanisms that large ones bury.
2. Differential Reasoning First
Before reading code, shrink the search space with diffs — they are cheaper than comprehension:
| It worked... | So ask... |
|---|---|
| ...before | What changed? git log -p the suspect paths; git bisect if the range is wide |
| ...on another machine / CI | What differs in environment? Versions, env vars, OS, locale, clean vs dirty state |
| ...with other inputs | What is special about this input? Minimize until the triggering property is obvious |
| ...in the other code path | Diff the two paths; the divergence point is the suspect list |
3. Hypothesis Ledger
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.
- 8d ago First seen · 84 lines · 37 tokens per session scan A 4f77661a3e86
debugger is an agent published in the GitHub repository madebyaris/advance-minimax-m3-cursor-rules (125 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 1,033 once invoked, about $0.0002 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.
Other agents, from other repositories
learnship-debugger
Investigates bugs using systematic hypothesis testing — traces from symptoms to root cause, writes investigation findings to the debug session file. Spawned by debug workflow on platforms with subagent support.
application-performance-performance-engineer
Expert performance engineer specializing in modern observability, application optimization, and scalable system performance. Masters OpenTelemetry, distributed tracing, load testing, multi-tier caching, Core Web Vitals, and performance monitoring. Handles end-to-end optimization, real user monitoring, and scalability…
cicd-automation-devops-troubleshooter
Expert DevOps troubleshooter specializing in rapid incident response, advanced debugging, and modern observability. Masters log analysis, distributed tracing, Kubernetes debugging, performance optimization, and root cause analysis. Handles production outages, system reliability, and preventive monitoring. Use…
code-refactoring-legacy-modernizer
Refactor legacy codebases, migrate outdated frameworks, and implement gradual modernization. Handles technical debt, dependency updates, and backward compatibility. Use PROACTIVELY for legacy system updates, framework migrations, or technical debt reduction.
architect
Deep reasoning agent. Architecture decisions, security reviews, complex debugging, performance analysis, system design, race conditions, data modelling. Use when getting it wrong has high cost.
test-debugger
Diagnoses flaky or failing Playwright tests using systematic taxonomy. Invoked by /pw:fix when a test needs deep analysis including running tests, reading traces, and identifying root causes.