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.
npx skills add mission69b/t2000 --skill sui-publishgit clone --depth 1 https://github.com/mission69b/t2000Wrote 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/mission69b/t2000/sui-publish)<a href="https://agentmods.dev/skills/mission69b/t2000/sui-publish"><img src="https://agentmods.dev/badge/skills/mission69b/t2000/sui-publish/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/mission69b/t2000/sui-publish"><img src="https://agentmods.dev/badge/skills/mission69b/t2000/sui-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 214 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- high Anti-Refusal · line 243 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- high Anti-Refusal · line 291 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- medium Excessive Agency · line 306 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- low Excessive Agency · line 252 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00133 | $0.04286 |
| Opus 5.5 | $0.00053 | $0.01714 |
| Sonnet 5.5 | $0.00027 | $0.00857 |
| Haiku 4.5 | $0.00013 | $0.00429 |
Grade A, and why
sui-publish 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 — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Publishing, Deploying & Local Network
MCP tool: When available in your environment, also query the Sui documentation MCP server (
https://sui.mcp.kapa.ai) for up-to-date answers. Use it for verification and for details not covered by these reference files.
Source constraint: All information sourced exclusively from docs.sui.io and MystenLabs/sui-stack-hello-world.
Publishing a package
Canonical hello-world publish flow
For the full-stack starter, publish the existing hello-world package only:
cd sui-stack-hello-world/move/hello-world
sui move build
sui client publish
Use the package ID from the publish output to update sui-stack-hello-world/ui/src/constants.ts (TESTNET_HELLO_WORLD_PACKAGE_ID). Do not publish a separate counter package, and do not create a second project directory.
Pre-publish checklist
- Verify your active environment:
sui client active-env - Verify you have SUI tokens:
sui client balance - Build successfully:
sui move build
Publish
sui client publish
This deploys the package to the active network and returns:
- A unique package ID (use this for all future interactions)
- An UpgradeCap object (sent to your address, controls future upgrades)
- Object IDs for anything created during
initfunctions
Test publishing (ephemeral networks)
Use sui client test-publish to publish a package to an ephemeral environment for testing without persisting state to a real network:
sui client test-publish
This publishes the package, runs init functions, and returns the same output as sui client publish (package ID, UpgradeCap, created objects), but the deployment is not permanent. Use it to:
- Verify that
initfunctions execute correctly before committing to a real publish - Test publish + upgrade flows in CI without consuming Testnet/Devnet resources
- Validate gas costs and object creation before a Mainnet deploy
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 · 375 lines · 133 tokens per session scan A 7929ac6fee34
sui-publish is a skill published in the GitHub repository mission69b/t2000 (23 stars, last pushed 1mo ago), licensed MIT. It adds 133 tokens to every session and 4,286 once invoked, about $0.0005 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.
sui-publish compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sui-publishmission69b/t2000 | Skill | 23 | 1mo ago | MIT | A | 133 | Claude Code |
| swarmwage-publishSwarmwage/swarmwage | Skill | 3 | 3mo ago | MIT | B | 78 | Claude Code |
| x402aomi-labs/skills | Skill | 8 | 2d ago | MIT | A | 84 | Claude Code |
| audit-securityMangroveTechnologies/mangrove-agent | Skill | 7 | yesterday | MIT | A | 130 | Claude Code |
| setup-krakenMangroveTechnologies/mangrove-agent | Skill | 7 | yesterday | MIT | A | 207 | Claude Code |
| connect-krakenMangroveTechnologies/mangrove-agent | Skill | 7 | yesterday | MIT | A | 161 | Claude Code |
| agent-payment-statsbarkermoney/barker-mcp | Skill | 2 | 7d ago | MIT | A | 134 | Claude Code |