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/threat-triage)<a href="https://agentmods.dev/commands/wyre-ai/msp-claude-plugins/threat-triage"><img src="https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/threat-triage/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/threat-triage"><img src="https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/threat-triage.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 | $0.00015 | $0.01260 |
| Opus 5.5 | $0.00006 | $0.00504 |
| Sonnet 5.5 | $0.00003 | $0.00252 |
| Haiku 4.5 | $0.00002 | $0.00126 |
Grade A, and why
threat-triage 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Threat Triage
Triage recent email threats detected by Abnormal Security, prioritized by severity and attack type.
Prerequisites
- Valid Abnormal Security API token configured (ABNORMAL_API_TOKEN)
- API token must have threat detection read permissions
Steps
-
Build search filter
- Parse all provided arguments
- Map text values to API codes (type, severity, status)
- Construct OData filter expression
-
Fetch recent threats
GET /v1/threats?filter=...&pageSize=... Authorization: Bearer <token> -
Sort by priority
- Critical severity first, then High, Medium, Low
- Within same severity, BEC and supply chain threats first
-
Format triage report
- Display threat list with key details
- Include severity indicators and recommended actions
Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| severity | string | No | - | critical/high/medium/low |
| type | string | No | - | bec/phishing/malware/extortion/scam/spam/supply-chain |
| status | string | No | not-remediated | remediated/not-remediated/post-remediated/all |
| start-date | string | No | 24h ago | ISO 8601 date |
| end-date | string | No | now | ISO 8601 date |
| limit | int | No | 25 | Max results (1-100) |
Examples
Triage All Recent Threats
/threat-triage
Critical Threats Only
/threat-triage --severity critical
BEC Threats This Week
/threat-triage --type bec --start-date "2026-03-20T00:00:00Z"
All Threats Including Remediated
/threat-triage --status all --limit 50
Output
Abnormal Security Threat Triage (last 24 hours)
================================================
Found 8 unremediated threats
+-----------+------------------+----------+---------------------+-----------------------------------+-------------------+
| Threat ID | Attack Type | Severity | Sender | Subject | Received |
+-----------+------------------+----------+---------------------+-----------------------------------+-------------------+
| 184def76 | BEC | Critical | [email protected] | Urgent: Wire Transfer Request | 2026-03-27 09:15 |
| 29abc134 | Supply Chain | Critical | [email protected] | Updated Payment Details | 2026-03-27 08:42 |
| 3f4e5d6c | Credential Phish | High | [email protected]| Verify Your Account | 2026-03-27 07:30 |
| 4a5b6c7d | Malware | High | [email protected] | Invoice #8821 Attached | 2026-03-27 06:15 |
| 5b6c7d8e | Credential Phish | High | [email protected] | Shared Document Ready | 2026-03-26 22:10 |
| 6c7d8e9f | Extortion | Medium | [email protected] | We Have Your Data | 2026-03-26 20:45 |
| 7d8e9f0a | Scam | Medium | [email protected] | Invoice Payment Overdue | 2026-03-26 18:30 |
| 8e9f0a1b | Spam | Low | [email protected] | Limited Time Offer! | 2026-03-26 16:00 |
+-----------+------------------+----------+---------------------+-----------------------------------+-------------------+
Summary:
- Critical: 2 | High: 3 | Medium: 2 | Low: 1
- Types: BEC (1), Supply Chain (1), Credential Phishing (2), Malware (1), Extortion (1), Scam (1), Spam (1)
- Auto-Remediated: 0 | Not Remediated: 8
Priority Actions:
1. Investigate BEC threat 184def76 - wire transfer request targeting CFO
2. Investigate Supply Chain threat 29abc134 - vendor payment redirect
3. Remediate credential phishing threats 3f4e5d6c, 5b6c7d8e
Quick Actions:
- View threat details: /search-threats --type bec
- Inspect one threat: abnormal_threats_get with the threat UUID
- Remediate: abnormal_messages_list, then abnormal_remediation_manage per message
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 · 136 lines · 15 tokens per session scan A 4298a8e92a81
threat-triage 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 15 tokens to every session and 1,260 once invoked, about $0.0001 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.