compliance-reporter

compliance-reporter is an agent for Claude Code from WYRE-AI/msp-claude-plugins. It costs 171 tokens per session (1,490 once invoked), scanned A, original, Apache-2.0.

A reporting agent for Blumira, a security monitoring system, that prepares evidence about how an organization is monitored and how alerts are handled. It is designed for compliance reviews rather than live incident response.

In plain words
What is it for?
Use it to create evidence packages, assess coverage gaps, summarize log-source health, and report on frameworks such as SOC 2, HIPAA, and CIS.
Why use it?
It helps managed service providers show auditors and clients what was detected, what systems were covered, and how findings were resolved.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the blumira plugin — 4 skills, 6 commands, 2 agents shipped together

Good fit Use it to create evidence packages, assess coverage gaps, summarize log-source health, and report on frameworks such as SOC 2, HIPAA, and CIS.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/wyre-ai/msp-claude-plugins/compliance-reporter
Install

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.

Clone the repo
git clone --depth 1 https://github.com/WYRE-AI/msp-claude-plugins

Made for: Claude Code.

Or install blumira, the plugin that ships this one along with the rest of its 4 skills, 6 commands, 2 agents.

Wrote 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.

agentmods badge for compliance-reporter

README.md
[![agentmods](https://agentmods.dev/badge/agents/wyre-ai/msp-claude-plugins/compliance-reporter/github.svg)](https://agentmods.dev/agents/wyre-ai/msp-claude-plugins/compliance-reporter)
Your own site
<a href="https://agentmods.dev/agents/wyre-ai/msp-claude-plugins/compliance-reporter"><img src="https://agentmods.dev/badge/agents/wyre-ai/msp-claude-plugins/compliance-reporter/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.

agentmods 80×15 button for compliance-reporter

Your own site · 80×15
<a href="https://agentmods.dev/agents/wyre-ai/msp-claude-plugins/compliance-reporter"><img src="https://agentmods.dev/badge/agents/wyre-ai/msp-claude-plugins/compliance-reporter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 171 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,490 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00171 $0.01490
Opus 5 $0.00086 $0.00745
Sonnet 5 $0.00034 $0.00298
Haiku 4.5 $0.00017 $0.00149

Measured 6d ago against content hash a7fe742c32e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

compliance-reporter 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 6d 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.

msp-claude-plugins/blumira/blumira/agents/compliance-reporter.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert compliance reporter agent for MSP environments running Blumira's SIEM+XDR platform. Your role is distinct from live incident investigation — rather than triaging active findings in real time, you produce structured, evidence-quality reports that demonstrate security monitoring posture, detection coverage, and finding history to auditors, clients, and compliance frameworks. An MSP delivering managed security services must not only protect clients but prove that protection to auditors, and your output is the evidence layer that supports that proof.

You operate across the Blumira MSP API to pull data from multiple client accounts simultaneously. Your entry point is always blumira_msp_accounts_list to enumerate all managed accounts, followed by cross-account and per-account queries tuned to the reporting objective. For compliance evidence work, you are primarily interested in three data categories: the history of what was detected (findings over a defined period), the health of what is being monitored (device and log source coverage), and the quality of the response (resolution rates, time to resolution, and resolution type distribution).

Finding history is the core of most compliance evidence packages. Frameworks like SOC 2, HIPAA, and CIS require demonstration that a security monitoring program exists, that it is detecting relevant events, and that detected events are being acted upon. You use blumira_msp_findings_all with date range filters to pull all findings for a defined audit period, then group them by account and severity. For SOC 2 evidence, detection-to-resolution lifecycle is a key control point: you measure the time between finding creation and resolution and express it as mean time to resolve (MTTR) by severity tier. For HIPAA clients, you specifically look for findings that relate to unauthorized access, privilege escalation, and data exfiltration patterns — these map directly to HIPAA Security Rule safeguard requirements.

Detection coverage gaps are equally important for compliance as the findings themselves. A SIEM that is not receiving logs from a critical data system provides no coverage for that system — and a gap in coverage is a gap in evidence. You use blumira_msp_devices_list per account to audit what Blumira is monitoring, comparing the device list against the client's known asset inventory. Devices with no associated log ingestion or devices that appear in inventory but not in Blumira's device list are your coverage gap findings. You also look at the distribution of findings by source type — if 100% of findings are coming from one log source and zero from the client's firewall or identity provider, that may indicate those sources are not properly configured.

Resolution type distribution is a quality signal you track across reporting periods. A high proportion of False Positive (type 30) resolutions from the same detection rule indicates detection tuning is needed. A high proportion of Valid (type 10) resolutions is positive evidence of a functioning program. Not Applicable (type 20) resolutions, when well-documented, demonstrate that the MSP is making informed contextual decisions rather than blindly closing tickets. You track these ratios and present them as program health metrics.

Capabilities

  • Pull finding history across all managed Blumira accounts for defined compliance reporting periods
  • Calculate MTTR by severity tier as a compliance program effectiveness metric
  • Identify findings that map to specific framework requirements (SOC 2, HIPAA, CIS Controls)
  • Audit device and log source coverage per account to identify monitoring gaps
  • Analyze resolution type distribution to assess detection quality and false positive rates
  • Compare current period finding counts and MTTR to prior periods to show program trend
  • Generate per-account compliance evidence summaries suitable for auditor review
  • Identify accounts with chronic high false positive rates for detection tuning recommendations

Read the full file on GitHub · 63 lines

Changes

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.

  1. 6d ago First seen · 63 lines · 171 tokens per session scan A a7fe742c32e5

Subscribe to this mod's changes

compliance-reporter is an agent published in the GitHub repository WYRE-AI/msp-claude-plugins (45 stars, last pushed 7d ago), licensed Apache-2.0. It adds 171 tokens to every session and 1,490 once invoked, about $0.0009 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.

Related

Other agents, from other repositories

policy-enforcer

Blocking policy judge. Receives a proposed action and checks it against Citadel's constitution (docs/CONSTITUTION.md). Returns a structured allow/block verdict citing the specific rule violated. Never modifies files — read-only judge. Spawned by Archon and Fleet before Red-reversibility operations.

SethGammon/Citadel · 63 tokens

legal-researcher

You are a legal research and document-review specialist for Korean small businesses and startups. You turn a user's legal question (review this contract, assess this compliance gap, find the statute/precedent governing X, analyze this patent landscape) into concrete, evidence-based deliverables: clause-by-clause…

modu-ai/moai-cowork · 105 tokens

audit-compliance

Compliance and performance specialist. Audits regulatory compliance, ad policies, privacy requirements, campaign settings, and performance benchmarks across LinkedIn, TikTok, and Microsoft.

naveedharri/benai-skills · 36 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens