Sui is a blockchain platform for running smart contracts and managing digital assets, using the Move programming language and a network of authorities to process transactions. It is intended for developers building web3 applications and on-chain assets.
Borrowing it
Nothing to install: this file belongs to MystenLabs/sui. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MystenLabs/sui/main/.claude/skills/simtest-debug/SKILL.mdgit clone --depth 1 https://github.com/MystenLabs/suiWrote 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/skills/mystenlabs/sui/simtest-debug)<a href="https://agentmods.dev/skills/mystenlabs/sui/simtest-debug"><img src="https://agentmods.dev/badge/skills/mystenlabs/sui/simtest-debug/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/skills/mystenlabs/sui/simtest-debug"><img src="https://agentmods.dev/badge/skills/mystenlabs/sui/simtest-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00025 | $0.01316 |
| Opus 5.5 | $0.00010 | $0.00526 |
| Sonnet 5.5 | $0.00005 | $0.00263 |
| Haiku 4.5 | $0.00003 | $0.00132 |
Grade A, and why
simtest-debug 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 1mo 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug a simtest failure
Debugs a simtest failure using logging and the scientific method.
Usage
/debug-simtest <repro command or test>
Example: /debug-simtest MSIM_TEST_SEED=1768248386016 RUST_LOG=sui=debug,info cargo simtest --test address_balance_tests test_deposit_and_withdraw
Example: `/debug-simtest test_deposit_and_withdraw
Arguments
$ARGUMENTS should contain either:
- a command to run to reproduce the test failure
- the name of a test
Instructions
This skill logs its progress to a file called NOTEBOOK.md in the repo root. The file should look like
# iteration 1
- OBSERVATIONS
- <observation 1>
- <observation 2>
- ...
- HYPOTHESIS: <description of hypothesis>
- EXPERIMENT: <description of experiment>
- RESULTS: <did the experiment confirm or refute the hypothesis?>
# iteration 2
<more observations, hypothesis, etc>
While executing the skill, never make functional changes to the code. Only add logging statements as described below. The goal is to find the root cause, not fix the issue. If at any point the reproduction command stops failing, or fails in a different way, this indicates that functional changes have been made. The test is deterministic and cannot be affected by emitting logs, doing expensive computations, etc.
Log File Management
Log files should be named consistently using the experiment number: experiment_N.log (e.g., experiment_1.log, experiment_2.log, etc.).
- Never delete log files during the debugging session - the user will clean them up when debugging is complete.
- Do not commit log files to git - they are too large.
Commit Strategy
After each experiment:
- Commit only the logging changes (code modifications) with a message indicating the experiment number:
CLAUDE: experiment N logging - Make a separate commit for NOTEBOOK.md updates with a message like
CLAUDE: experiment N observations
This keeps the debugging history clean and allows easy navigation between experiments. Do not include log files in any commits.
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.
- 1mo ago First seen · 118 lines · 25 tokens per session scan A c1556712e13c
simtest-debug is a skill published in the GitHub repository MystenLabs/sui (7,784 stars, last pushed today), licensed Apache-2.0. It adds 25 tokens to every session and 1,316 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 skills, from other repositories
foundry-testing
Write and debug Foundry tests and Solidity scripts. Use when writing unit, fuzz, fork, or invariant tests, writing bulloak BTT .tree specs (Branching Tree Technique), using cheatcodes, benchmarking gas, measuring coverage, writing deploy scripts, or working in tests/ or script/.
blockchain-application
Use this skill when asked about smart contract development, Solidity, Vyper, Rust smart contracts (Solana, NEAR, Polkadot), Haskell/Plutus (Cardano), Cairo/StarkNet, dApp backend development, Truffle, Hardhat, Foundry, Anchor, and blockchain application patterns. Languages: Solidity, Vyper, Rust, Haskell, Cairo, Move.…
spoonos-testing-patterns
Test SpoonOS agents effectively. Use when writing unit tests, integration tests, mocking LLM responses, or debugging agent behavior.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.