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/case-review)<a href="https://agentmods.dev/commands/wyre-ai/msp-claude-plugins/case-review"><img src="https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/case-review/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/case-review"><img src="https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/case-review.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 | $0.00011 | $0.01296 |
| Opus 5.5 | $0.00004 | $0.00518 |
| Sonnet 5.5 | $0.00002 | $0.00259 |
| Haiku 4.5 | $0.00001 | $0.00130 |
Grade A, and why
case-review 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 1mo 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Case Review
Review and triage abuse mailbox cases in Abnormal Security. These are user-reported suspicious emails that have been analyzed by Abnormal's AI.
Prerequisites
- Valid Abnormal Security API token configured (ABNORMAL_API_TOKEN)
- API token must have abuse mailbox/cases read permissions
Steps
-
Build case filter
- Parse all provided arguments
- Construct OData filter expression for overallStatus and judgment
-
Fetch cases
GET /v1/cases?filter=...&pageSize=... Authorization: Bearer <token> -
Sort and prioritize
- Malicious judgments first
- Then by severity and report time
-
Format triage report
- Display case list with AI judgment
- Include recommended actions per case
Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| status | string | No | open | open/acknowledged/done/all |
| judgment | string | No | - | malicious/spam/safe/no-action-needed |
| start-date | string | No | 7d ago | ISO 8601 date |
| end-date | string | No | now | ISO 8601 date |
| limit | int | No | 25 | Max results (1-100) |
Examples
Review All Open Cases
/case-review
Malicious Cases Only
/case-review --judgment malicious
All Cases This Month
/case-review --status all --start-date "2026-03-01"
Acknowledged Cases Needing Follow-Up
/case-review --status acknowledged
Output
Abuse Mailbox Case Review (last 7 days)
========================================
Found 6 open cases
+---------+------------+-------------------+----------------------------+-----------------------------------+-----------+
| Case ID | Judgment | Reported By | Sender | Subject | Reported |
+---------+------------+-------------------+----------------------------+-----------------------------------+-----------+
| 12345 | Malicious | [email protected] | [email protected] | Urgent: Wire Transfer | 03-27 09h |
| 12346 | Malicious | [email protected] | [email protected] | Verify Your Account Now | 03-27 08h |
| 12347 | Spam | [email protected] | [email protected] | Amazing Offer Just For You | 03-26 16h |
| 12348 | Spam | [email protected] | [email protected] | Monthly Newsletter | 03-26 14h |
| 12349 | Safe | [email protected] | [email protected] | Invoice #4521 | 03-26 11h |
| 12350 | No Action | [email protected] | [email protected] | Phishing Awareness Test | 03-25 15h |
+---------+------------+-------------------+----------------------------+-----------------------------------+-----------+
Summary:
- Malicious: 2 | Spam: 2 | Safe: 1 | No Action Needed: 1
Recommended Actions:
1. Case 12345 (Malicious BEC) - REMEDIATE across organization
2. Case 12346 (Malicious Phishing) - REMEDIATE across organization
3. Cases 12347-12348 (Spam) - DISMISS
4. Case 12349 (Safe) - DISMISS, reply to reporter confirming safe
5. Case 12350 (Phishing Simulation) - DISMISS
Quick Actions:
- View case details: Use abnormal_cases_get with the numeric case ID
- Remediate the mail behind a case: find the threat, then
abnormal_messages_list + abnormal_remediation_manage per message
- Dismiss / acknowledge / close: Abnormal portal only — no tool does this
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.
- 1mo ago First seen · 157 lines · 11 tokens per session scan A b27dde45454f
case-review is a command published in the GitHub repository WYRE-AI/msp-claude-plugins (49 stars, last pushed 4d ago), licensed Apache-2.0. It adds 11 tokens to every session and 1,296 once invoked, about $0.0000 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.
Other commands, from other repositories
vibe-check
Audit a vibe-coded app across the six things that actually block shipping, and get a prioritized fix list.
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.
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.