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 atom2ueki/mcp-server-synology --skill synology-nasgit clone --depth 1 https://github.com/atom2ueki/mcp-server-synologyWrote 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/atom2ueki/mcp-server-synology/synology-nas)<a href="https://agentmods.dev/skills/atom2ueki/mcp-server-synology/synology-nas"><img src="https://agentmods.dev/badge/skills/atom2ueki/mcp-server-synology/synology-nas/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/atom2ueki/mcp-server-synology/synology-nas"><img src="https://agentmods.dev/badge/skills/atom2ueki/mcp-server-synology/synology-nas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 Privilege Escalation · line 127 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Excessive Agency · line 107 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.
- medium Excessive Agency · line 110 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.
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 | $0.00212 | $0.02233 |
| Opus 5.5 | $0.00085 | $0.00893 |
| Sonnet 5.5 | $0.00042 | $0.00447 |
| Haiku 4.5 | $0.00021 | $0.00223 |
Grade A, and why
synology-nas 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 23d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synology NAS
This skill teaches you how to use the mcp-server-synology MCP effectively. The MCP exposes ~80 tools across seven domains; the trick is picking the right tool, targeting the right NAS, and not exploding a single user request into a dozen redundant calls.
Mental model
Three things shape almost every interaction:
- Targeting — most setups have one NAS and you can omit the target argument. Multi-NAS setups require a
nas_name(orbase_url) on every tool call. Don't guess; discover first. - State — auth is session-based and usually auto-managed. You almost never need to call
synology_loginyourself. Check status first; only log in if status says you must. - Aggregation — several individual tools have a *_summary equivalent. When the user wants a "checkup" or "overview," reach for the aggregate. When they want a specific number, use the targeted tool.
Once those three are settled, the rest is picking the right domain.
Always start here
Before any operation, run discovery — it's two cheap calls and answers "which NAS?" and "am I logged in?":
synology_list_nas— lists configured NAS units with names, URLs, connection status.synology_status— shows which sessions are active.
If the user mentions a NAS by name (e.g. "the backup NAS", "nas2"), match it to a nas_name from synology_list_nas. If only one NAS is configured, you can omit nas_name on subsequent calls. If multiple are configured and the user is ambiguous, ask which one — don't pick.
Tool call shape
Every operational tool accepts an optional target argument:
nas_name(preferred) — the identifier from settings.json, e.g."nas1".base_url— fallback when the NAS isn't in settings.json.
Pass at most one. Omit both only when there's a single NAS configured.
Path arguments must start with /. User-facing data lives under /volume1/ (or /volume2/, etc., for additional volumes). The root / lists shares; /homes, /photo, /video etc. are share-level mount points underneath. Don't invent paths — list the parent first if unsure.
What ships with it
9 files 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.
- 23d ago Changed · +2 lines f8abd3b0dbbc
- 2mo ago First seen · 128 lines · 212 tokens per session scan A 653c7bd9505b
synology-nas is a skill published in the GitHub repository atom2ueki/mcp-server-synology (245 stars, last pushed 24d ago), licensed MIT. It adds 212 tokens to every session and 2,233 once invoked, about $0.0008 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.
synology-nas compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| synology-nasatom2ueki/mcp-server-synology | Skill | 245 | 24d ago | MIT | A | 212 | Claude Code, Codex |
| unifi-protectsirkirby/unifi-mcp | Skill | 1.0k | today | MIT | A | 112 | Claude Code |
| unifi-accesssirkirby/unifi-mcp | Skill | 1.0k | today | MIT | A | 70 | Claude Code |
| network-health-checksirkirby/unifi-mcp | Skill | 1.0k | today | MIT | A | 49 | Claude Code |
| unifi-networksirkirby/unifi-mcp | Skill | 1.0k | today | MIT | A | 83 | Claude Code |
| unifi-access-supportsirkirby/unifi-mcp | Skill | 1.0k | today | MIT | A | 31 | Claude Code |
| qmclaw-workbenchxi-zhao/OpenQuantum | Skill | 71 | today | MIT | A | 124 | Codex |