soc

A command set for security-operations work in CrowdStrike NGSIEM. It routes requests such as triage, daily review, tuning, and threat hunting through the SOC workflow.

In plain words
What is it for?
Triageing alerts, reviewing untriaged alerts, tuning detections, hunting for threats, and showing available subcommands.
Why use it?
It provides named commands for common security-analysis tasks and applies the workflow's operating rules.

Command

Part of the crowdstrike-soc plugin — 1 skill, 1 command shipped together

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.

agentmods
npx agentmods add commands/willwebster5/agent-skills/soc
Clone the repo
git clone --depth 1 https://github.com/willwebster5/agent-skills

Or install crowdstrike-soc, the plugin that ships this one along with the rest of its 1 skill, 1 command.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 365 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00365
Opus 5 $0.00000 $0.00182
Sonnet 5 $0.00000 $0.00073
Haiku 4.5 $0.00000 $0.00036

Measured 3d ago against content hash b58dc01a890c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

soc 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 3d 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.

plugins/crowdstrike-soc/commands/soc.md · 39 lines

What it actually says

<rules priority="critical">
    <rule>Always invoke the soc skill for processing</rule>
    <rule>Never modify detection templates without explicit user approval</rule>
    <rule>Update .claude/skills/soc/memory/ files after every triage session per the Living Documents protocol</rule>
    <rule>Suggest environmental-context.md updates when new context is discovered during investigation</rule>
    <rule>Follow the principle of least filtered — FP is always better than a missed TP</rule>
</rules>

<actions>
    <action trigger="starts-with:triage">
        Triage the alert. Follow the soc skill workflow.
    </action>

    <action trigger="starts-with:daily">
        Review today's untriaged alerts. Follow the soc skill daily mode workflow.
    </action>

    <action trigger="starts-with:tune">
        Tune the specified detection. Follow the soc skill tuning workflow.
    </action>

    <action trigger="starts-with:hunt">
        Hunt for threats. Follow the soc skill hunt mode workflow.
    </action>

    <action trigger="default">
        Show available subcommands:

        /soc triage &lt;alert-url-or-id&gt;  — Triage a specific alert (full lifecycle)
        /soc daily [product]              — Review today's untriaged alerts (product: endpoint, ngsiem, identity, cloud_security)
        /soc tune &lt;detection-name&gt;       — Tune a detection (skip triage)
        /soc hunt &lt;description-or-IOCs&gt;  — Threat hunting mode
    </action>
</actions>
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. 3d ago First seen · 39 lines · 0 tokens per session scan A b58dc01a890c

Subscribe to this mod's changes

soc is a command published in the GitHub repository willwebster5/agent-skills (12 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 365 tokens. 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.