security-investigator: Skill for Claude Code

.github/skills/ai-agent-activity/SKILL.md

ai-agent-activity is a skill for Claude Code, Codex from SCStelz/security-investigator. It costs 194 tokens per session (17,130 once invoked), scanned A, original, MIT.

A reporting tool for seeing what AI agents in Microsoft 365 and Copilot environments actually do during use, including who used them, which tools ran, and what safety checks found.

In plain words
What is it for?
Use it to review agent users, prompts, replies, tool and connector calls, channels, token use, and Prompt Shield warnings over a period of time.
Why use it?
It helps distinguish an agent’s configured permissions from its real-world behavior. This makes it easier to spot unexpected use, risky prompts, or attempted jailbreaks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

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 →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is These are the compact, report-driving queries. The **full validated set** (Plane A 1a/4a/8a, Plane B 1b/4b/7b/8b, safety Query 9, session reconstruction 3a/3b, .

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/ai-agent-activity/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 ai-agent-activity

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/scstelz/security-investigator/ai-agent-activity"><img src="https://agentmods.dev/badge/skills/scstelz/security-investigator/ai-agent-activity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 194 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 17,130 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

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 →

  • medium Excessive Agency · line 305
    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 System Prompt Leakage · line 407
    Skill contains patterns that could indirectly extract system prompts through rephrasing, translation, summarization, or side-channel techniques.
    Fix: Guard against indirect extraction by refusing to summarize, translate, or rephrase system instructions. Add explicit anti-extraction clauses.
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 $0.00194 $0.17130
Opus 5 $0.00097 $0.08565
Sonnet 5 $0.00039 $0.03426
Haiku 4.5 $0.00019 $0.01713

Measured 11d ago against content hash f983d6d091c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ai-agent-activity 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 11d 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.

.github/skills/ai-agent-activity/SKILL.md · 910 lines

How it starts

The opening of the file, as written. The whole thing — 910 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Agent Activity — Instructions

Purpose

This skill reports the runtime activity of AI agents built on Agent 365 / Copilot Studio / Microsoft 365 Copilot / Work IQ across a tenant — who invoked which agents, what tools and connectors ran, over which channels, with what token/inference usage, and what the content-safety layer (Prompt Shield jailbreak / XPIA) caught.

It answers "what are the agents actually doing?" — the behavioral counterpart to the configuration-focused ai-agent-posture skill.

ai-agent-posture (config) ai-agent-activity (this skill — runtime)
Question How are agents configured? (access, tools declared, data sources, credentials) What are agents doing? (prompts, tool calls, users, channels, safety flags)
Primary table AgentsInfo (Advanced Hunting) UnifiedAgentObservability (Data Lake) or CloudAppEvents (Defender)
Time model Point-in-time config snapshots Event stream over a lookback window
Use together Posture flags a broadly-accessible, email-capable agent Activity shows whether that agent is actually used, by whom, and whether it was jailbroken

Use them together: run ai-agent-posture to find the risky configurations, then run this skill to see which of those agents are active-and-dangerous at runtime.

References:

Read the full file on GitHub · 910 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. 11d ago First seen · 910 lines · 194 tokens per session scan A f983d6d091c4

Subscribe to this mod's changes

ai-agent-activity is a skill published in the GitHub repository SCStelz/security-investigator (245 stars, last pushed 3d ago), licensed MIT. It adds 194 tokens to every session and 17,130 once invoked, about $0.0010 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 2026-08-30.

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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 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