security-investigator: Skill for Claude Code

.github/skills/scope-drift-detection/device/SKILL.md

scope-drift-detection-device is a skill for Claude Code, Codex from SCStelz/security-investigator. It costs 148 tokens per session (13,354 once invoked), scanned A, original, MIT.

A device-security analysis that looks for gradual changes in the processes running on endpoints such as computers and servers.

In plain words
What is it for?
Use it to compare process activity with a device baseline, find new processes or accounts, spot unusual binaries and command patterns, and rank drift across a fleet.
Why use it?
It can reveal slow expansion of behavior that may not trigger alerts based only on sudden changes or fixed thresholds.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is SCStelz/security-investigator's own configuration. It tells Claude Code and Codex how to work on security-investigator itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything security-investigator configures →

Reuse

Borrowing it

Nothing to install: this file belongs to SCStelz/security-investigator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/SCStelz/security-investigator/main/.github/skills/scope-drift-detection/device/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/SCStelz/security-investigator

Made for: Claude Code, Codex.

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 scope-drift-detection-device

README.md
[![agentmods](https://agentmods.dev/badge/skills/scstelz/security-investigator/device/github.svg)](https://agentmods.dev/skills/scstelz/security-investigator/device)
Your own site
<a href="https://agentmods.dev/skills/scstelz/security-investigator/device"><img src="https://agentmods.dev/badge/skills/scstelz/security-investigator/device/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 scope-drift-detection-device

Your own site · 80×15
<a href="https://agentmods.dev/skills/scstelz/security-investigator/device"><img src="https://agentmods.dev/badge/skills/scstelz/security-investigator/device.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 148 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 13,354 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high YARA Match · line 560
    YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).
    Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
  • medium Excessive Agency · line 112
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Agent Snooping · line 964
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00148 $0.13354
Opus 5 $0.00074 $0.06677
Sonnet 5 $0.00030 $0.02671
Haiku 4.5 $0.00015 $0.01335

Measured 9d ago against content hash 4d9a5e95d24f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

scope-drift-detection-device scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Notable command-line patterns (Query 20):** Search for reconnaissance commands (`whoami`, `net user`, `ipconfig`, `nltest`, `systeminfo`), lateral movement (`psexec`, `wmic`), persistence mechanisms (`schtasks`, `reg
.github/skills/scope-drift-detection/device/SKILL.md · 970 lines

How it starts

The opening of the file, as written. The whole thing — 970 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Device Scope Drift Detection — Instructions

Purpose

This skill detects scope drift — the gradual, often imperceptible expansion of process execution behavior beyond an established baseline — in endpoints and devices. Unlike sudden compromise (which triggers alerts), scope drift is a slow-burn pattern that evades threshold-based detections.

Entity Type: Device

Identifier Primary Table(s) Use Case
DeviceName (hostname) DeviceProcessEvents Endpoints, servers, workstations — fleet-wide or single-device process baseline analysis

What this skill detects:

  • Volume spikes in process execution relative to historical baseline
  • New processes or process chains not seen in the baseline period
  • New service accounts or user contexts executing processes
  • Unsigned or unusually-signed binaries executing on endpoints
  • Reconnaissance, lateral movement, persistence, and exfiltration command patterns
  • Security alerts involving the drifting devices

Two operating modes:

Mode When to Use Scope
Fleet-wide "Check all devices for process drift", "device drift across the fleet" Computes per-device drift scores, ranks all devices, flags those > 150%
Single-device "Investigate process drift on DEVICE-01", specific hostname provided Deep dive on one device with full process inventory and command-line analysis

Related skills:


📑 TABLE OF CONTENTS

  1. Critical Workflow Rules - Start here!
  2. Output Modes - Inline chat vs. Markdown file
  3. Quick Start - 10-step investigation pattern
  4. Drift Score Formula - Weighted composite scoring (5 dimensions)
  5. Execution Workflow - Complete 4-phase process
  6. Sample KQL Queries - Validated query patterns (Queries 14-22)
  7. Report Template - Output format specification
  8. Known Pitfalls - Edge cases and false positives
  9. Error Handling - Troubleshooting guide
  10. SVG Dashboard Generation - Visual dashboard from report

Read the full file on GitHub · 970 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 970 lines · 148 tokens per session scan A 4d9a5e95d24f

Subscribe to this mod's changes

scope-drift-detection-device is a skill published in the GitHub repository SCStelz/security-investigator (244 stars, last pushed yesterday), licensed MIT. It adds 148 tokens to every session and 13,354 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens