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 yangtaihong59/siyuan-plugins-mcp-sisyphus --skill siyuan-mcp-system-safetygit clone --depth 1 https://github.com/yangtaihong59/siyuan-plugins-mcp-sisyphusWrote 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/yangtaihong59/siyuan-plugins-mcp-sisyphus/siyuan-mcp-system-safety)<a href="https://agentmods.dev/skills/yangtaihong59/siyuan-plugins-mcp-sisyphus/siyuan-mcp-system-safety"><img src="https://agentmods.dev/badge/skills/yangtaihong59/siyuan-plugins-mcp-sisyphus/siyuan-mcp-system-safety/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/yangtaihong59/siyuan-plugins-mcp-sisyphus/siyuan-mcp-system-safety"><img src="https://agentmods.dev/badge/skills/yangtaihong59/siyuan-plugins-mcp-sisyphus/siyuan-mcp-system-safety.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 | $0.00035 | $0.00899 |
| Opus 5 | $0.00017 | $0.00449 |
| Sonnet 5 | $0.00007 | $0.00180 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
siyuan-mcp-system-safety 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 13d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- siyuan-sisyphus-system-cli — 89% identical, 42 lines differ
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SiYuan System and Safety with MCP
Start with a connectivity check and inspect live help before unfamiliar actions.
system(action="get_version")
system(action="get_current_time")
notebook(action="get_permissions")
Notebook permissions are rwd, rw, r, and none. Missing content can mean permission filtering rather than absence. Record the current value before proposing a permission change.
Confirmation boundary
Obtain explicit approval before notebook/document/block deletion or move, bulk replacement, asset upload or deletion, local-path export, tag/card removal, permission changes, and workspace path disclosure. State the exact target and consequence. A prior request to inspect or diagnose is not approval to mutate.
system(action="conf", mode="summary")
system(action="network")
system(action="notify", msg="Task complete", level="info", timeout=5000)
extension(action="list", refresh=false)
Extension trust and lifecycle verification
Treat an extension package as executable third-party code. Keep these checks separate; passing one does not prove the next one:
- Static package check: inspect the package metadata and required files, exact
minAppVersion,backends,kernels, andfrontendsvalues, then review the source, entrypoint, handlers, and cleanup paths. A package validator can catch malformed or incompatible files, but it cannot prove that SiYuan loaded the package. - Actual loading: inspect the current runtime inventory and the user-visible enabled state. A package being present, discoverable, or statically valid is not evidence that its
onloador kernel entrypoint ran. - Registration and unregistration: for an approved live check, verify the lifecycle-owned surface after enablement (for example a frontend Agent action or plugin MCP tool), then disable/unload it and verify the same name is gone. Confirm that DOM nodes, listeners, timers, RPC methods, and MCP tools are cleaned up; the official
siyuan://help/action/extension/listbridge only reports tools exposed by SiYuan's/mcpregistry and is not a substitute for frontend UI evidence. - Reload and functional readback: use the supported reload path, then repeat discovery and one harmless surface-specific interaction. Check that the new behavior works once, old registrations are absent, and no duplicate handlers remain. Do not treat a refreshed tool list as proof that a plugin UI or desktop-only code path works.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 59 lines · 35 tokens per session scan A e8c56f367afd
siyuan-mcp-system-safety is a skill published in the GitHub repository yangtaihong59/siyuan-plugins-mcp-sisyphus (104 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 899 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…