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 WYRE-AI/msp-claude-plugins --skill retention-rpo-compliancegit 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/skills/wyre-ai/msp-claude-plugins/retention-rpo-compliance)<a href="https://agentmods.dev/skills/wyre-ai/msp-claude-plugins/retention-rpo-compliance"><img src="https://agentmods.dev/badge/skills/wyre-ai/msp-claude-plugins/retention-rpo-compliance/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/wyre-ai/msp-claude-plugins/retention-rpo-compliance"><img src="https://agentmods.dev/badge/skills/wyre-ai/msp-claude-plugins/retention-rpo-compliance.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 | $0.00094 | $0.01734 |
| Opus 5 | $0.00047 | $0.00867 |
| Sonnet 5 | $0.00019 | $0.00347 |
| Haiku 4.5 | $0.00009 | $0.00173 |
Grade A, and why
Retention & RPO Compliance 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 8d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retention & RPO Compliance
Overview
Retention and RPO commitments are made in two places that routinely drift apart: the
contract or SOW (what was promised — "1-year retention," "4-hour RPO") and the actual
backup system configuration (what's actually happening — a 90-day local retention
policy, a nightly-only backup schedule). Nobody discovers the gap until a restore
request for month 8 of a promised 12-month retention window comes back empty, or a
ransomware event reveals that the "4-hour RPO" client's most recent recovery point is
actually 22 hours old. This skill exists to find that gap proactively by comparing
what's promised against what's configured — not to audit whether backups are running
(backup-job-health) or recoverable (restore-test-verification), both of which are
prerequisites to this check actually meaning anything.
Anti-triggers
- Framework or control compliance — "compliance" here means a contracted
retention window and RPO target, not CIS/SOC 2/HIPAA control evidence; for
that use
evidence-mappingin compliance-pack. - Reading the agreement itself — pulling a client's contract terms,
services, or renewal dates is the PSA's surface; use
autotask-contractsorhalopsa-contracts.
Key Concepts
Retention: contracted vs. configured
Retention is the length of time recovery points remain available for restore. The check here is mechanical but frequently skipped: pull the contracted/required retention value (from a documentation platform, contract record, or explicit org policy) and the actual configured retention window from the backup/BCDR tool itself, and compare them directly.
Two distinct gap types matter differently:
- Configured-shorter-than-contracted — e.g. contract specifies 1-year retention, appliance is configured for 90 days. This is a direct compliance failure: the MSP is not delivering what was promised, and a restore request past the configured window will simply fail. Always the higher-severity finding.
- Storage-forced truncation — retention is configured correctly, but the
appliance is running out of local storage and silently purging older recovery
points before the configured window elapses (see
backup-job-health's storage- trending section for the leading indicator). This is a compliance failure with a different root cause and a different fix (capacity, not configuration) — report it distinctly rather than merging it with a simple misconfiguration.
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.
- 8d ago First seen · 156 lines · 94 tokens per session scan A f74c082fdaf4
Retention & RPO Compliance is a skill published in the GitHub repository WYRE-AI/msp-claude-plugins (45 stars, last pushed 9d ago), licensed Apache-2.0. It adds 94 tokens to every session and 1,734 once invoked, about $0.0005 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 skills, from other repositories
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
design-copywriting
A copywriting workflow for marketing and product pages that uses a brand voice and returns structured text for page sections.
content-card-news
A planning tool for four-card social media carousels on Instagram, Threads, and Kakao Channel, combining card copy, design guidance, image prompts, captions, and hashtags.
cs-voc-triage
A customer-feedback analysis tool that combines reviews and support contacts from multiple channels. VOC means “voice of the customer”: the comments, questions, complaints, and praise customers leave about a business.
lead-intelligence
Deep-research lead intelligence gathering for B2B qualified leads. This skill runs in two layers.