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/WYRE-AI/msp-claude-pluginsWrote 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/commands/wyre-ai/msp-claude-plugins/backup-status)<a href="https://agentmods.dev/commands/wyre-ai/msp-claude-plugins/backup-status"><img src="https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/backup-status.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 | $0.00017 | $0.00710 |
| Opus 5 | $0.00009 | $0.00355 |
| Sonnet 5 | $0.00003 | $0.00142 |
| Haiku 4.5 | $0.00002 | $0.00071 |
Grade A, and why
backup-status 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 4d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backup Status
Cross-vendor, portfolio-wide backup job health snapshot: active failure count, missed backups, at-risk clients, and storage trends — pulled from whatever backup and BCDR tools the org has connected through the gateway.
Prerequisites
- WYRE MCP Gateway connected (
conduit) with at least one backup/BCDR connector (Datto BCDR, Datto SaaS Protection, Spanning, or Unitrends). Without one, there is no backup job data to report on.
Steps
-
Discover available tools. Call
conduit__search_toolsto determine which backup/BCDR connectors are live and what their actual tool names are (e.g.datto-bcdr__list_devices,spanning__list_jobs). Never assume a specific vendor's tool surface — a portfolio commonly has more than one backup/BCDR tool connected at once (an on-prem appliance plus a SaaS-backup tenant). -
Invoke the
backup-health-auditoragent for the full portfolio (no client scope). The agent normalizes image-based appliance backups and SaaS-data snapshot backups into one comparable health view per thebackup-job-healthskill. -
Assemble and return the snapshot, in the order: active failure streaks → missed backups → storage risk → healthy summary. Lead with whichever category has the most urgent finding if one clearly dominates (e.g., a mission-critical system with a multi-night failure streak).
Arguments
This command takes no arguments — it always reports the full portfolio across
whatever backup/BCDR tools are connected. Use /backup-pack:restore-check [client]
or /backup-pack:retention-audit [client] to scope to a single client.
Examples
Basic Usage
/backup-pack:backup-status
Output
================================================================================
Backup Status — [Date]
================================================================================
ACTIVELY FAILING
--------------------------------------------------------------------------------
[Client] — [protected unit] ([vendor]): [N] consecutive failures, last success [date]
...
MISSED BACKUPS
--------------------------------------------------------------------------------
[Client] — [protected unit] ([vendor]): no run recorded since [date]
...
STORAGE RISK
--------------------------------------------------------------------------------
[Client] — [appliance/tenant]: [approaching capacity X% / anomalous growth]
...
PORTFOLIO SUMMARY
--------------------------------------------------------------------------------
Protected units assessed: [N]
Healthy: [N]
Actively failing: [N]
Missed: [N]
Storage risk: [N]
================================================================================
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.
- 4d ago First seen · 95 lines · 17 tokens per session scan A 81bde4247a82
backup-status is a command published in the GitHub repository WYRE-AI/msp-claude-plugins (45 stars, last pushed 5d ago), licensed Apache-2.0. It adds 17 tokens to every session and 710 once invoked, about $0.0001 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 2026-09-04.
Other commands, from other repositories
resolve-codeql
Analyze and resolve CodeQL alerts systematically.
site-audit
Crawl a website and audit for broken links, spelling errors, console errors, and visual issues.
check
Run static analysis on the Java project — detects configured tools (Checkstyle, SpotBugs, PMD) and reports findings.
analyze-issue
A command that runs a systematic problem investigation and searches for the root cause through a five-agent analysis process.
quick-analyze
A command for quickly analysing a problem when you already have a clear error message.
checklist
Generate a custom checklist for the current feature based on user requirements.