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/retention-audit)<a href="https://agentmods.dev/commands/wyre-ai/msp-claude-plugins/retention-audit"><img src="https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/retention-audit/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/commands/wyre-ai/msp-claude-plugins/retention-audit"><img src="https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/retention-audit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01082 |
| Opus 5 | $0.00009 | $0.00541 |
| Sonnet 5 | $0.00003 | $0.00216 |
| Haiku 4.5 | $0.00002 | $0.00108 |
Grade A, and why
retention-audit 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 5d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retention Audit
Compares actual backup retention configuration and achievable RPO against contracted
or documented requirements, for one client or the whole portfolio. Surfaces gaps
where configured retention falls short of what was promised, where storage capacity
is silently forcing retention shorter than configured, and where current backup
cadence/reliability can't actually meet a contracted recovery point objective. Omit
client to run across the whole portfolio.
Prerequisites
- Conduit MCP Gateway connected (
conduit) - At least one backup/BCDR connector (Datto BCDR, Datto SaaS Protection, Spanning, or Unitrends) for the target client(s)
- A documented retention/RPO requirement (IT Glue, Hudu, or PSA contract record) is helpful but not required — without one, this run reports configured values as informational and flags the missing documentation as its own finding
Steps
- Discover available tools. Call
conduit__search_toolsto confirm which backup/BCDR connectors — and, optionally, documentation/PSA connectors — are available. - Scope the run. If
clientis given, resolve it to its protected units and any documented retention/RPO requirement. If omitted, enumerate all clients with at least one connected backup/BCDR tool and run the audit for each. - Invoke the
retention-compliance-auditoragent for the resolved scope. The agent pulls actual configured retention and backup cadence, locates the contracted/required values where documented, and computes both the retention gap (with configuration-gap vs. storage-forced-truncation classified separately) and the achievable-RPO-vs-target comparison. - Present the report, largest retention shortfalls and most severe RPO misses first, followed by the full compliance tables and missing-documentation findings.
- If portfolio-wide, close with a rollup ranking clients by gap severity.
Arguments
| Argument | Required | Default | Description |
|---|---|---|---|
client |
No | — (portfolio-wide) | The client/organization name to audit retention/RPO compliance for. Omit to run across every client with a connected backup/BCDR tool. |
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.
- 5d ago First seen · 133 lines · 17 tokens per session scan A fe624e868a75
retention-audit is a command published in the GitHub repository WYRE-AI/msp-claude-plugins (45 stars, last pushed 6d ago), licensed Apache-2.0. It adds 17 tokens to every session and 1,082 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.