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.
npx agentmods add instructions/zenidp/verisift/claude-mdgit clone --depth 1 https://github.com/Zenidp/verisiftWrote 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/instructions/zenidp/verisift/claude-md)<a href="https://agentmods.dev/instructions/zenidp/verisift/claude-md"><img src="https://agentmods.dev/badge/instructions/zenidp/verisift/claude-md.svg" alt="Measured on agentmods" 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 | $0.03807 | $0.03807 |
| Opus 5 | $0.01903 | $0.01903 |
| Sonnet 5 | $0.00761 | $0.00761 |
| Haiku 4.5 | $0.00381 | $0.00381 |
Grade B, and why
verisift CLAUDE.md scanned grade B 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 4d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo mkdir -p /mnt/ewf_rd01 /mnt/rd01 How it starts
The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Course: SANS FOR508 — Advanced Incident Response, Threat Hunting & Digital Forensics Scenario: Stark Research Labs (SRL) — Lab 1.1 APT Incident Response Challenge
Case Overview
| Field | Value |
|---|---|
| Client | Stark Research Labs (SRL) |
| Domain | SHIELDBASE (Windows Server 2022, 2022 DFL) |
| Threat Actor | CRIMSON OSPREY (state-level APT) |
| Incident Declared | 2023-01-24 |
| Your Role | External IR consultant |
| Initial Responders | Roger Sydow (IT Admin), Clint Barton (IT Security Analyst) |
Evidence Files
| File | System | Notes |
|---|---|---|
/cases/srl/base-dc-cdrive.E01 |
dc01 — Domain Controller | C: drive (~12.5 GB) |
/cases/srl/base-rd01-cdrive.E01 |
rd01 — Remote Desktop Server | C: drive (~16.6 GB) — primary compromise host |
/cases/memory/rd01-memory.img |
rd01 | RAM capture (5 GB, primary analysis image) |
/cases/srl/base-rd_memory.img |
rd01 | RAM capture (3 GB, baseline-era image) |
/cases/srl/base-dc_memory.img |
dc01 | RAM capture (5 GB) |
Read-only — do NOT modify evidence files.
Output all analysis to ./analysis/, ./exports/, or ./reports/ (relative to /cases/srl/).
Common Commands
Mount E01 images (read-only)
# Mount rd01 C: drive
sudo mkdir -p /mnt/ewf_rd01 /mnt/rd01
sudo ewfmount /cases/srl/base-rd01-cdrive.E01 /mnt/ewf_rd01
sudo mount -o ro,loop,noatime /mnt/ewf_rd01/ewf1 /mnt/rd01
# Mount dc01 C: drive
sudo mkdir -p /mnt/ewf_dc01 /mnt/dc01
sudo ewfmount /cases/srl/base-dc-cdrive.E01 /mnt/ewf_dc01
sudo mount -o ro,loop,noatime /mnt/ewf_dc01/ewf1 /mnt/dc01
# Unmount when done
sudo umount /mnt/rd01 && sudo umount /mnt/ewf_rd01
sudo umount /mnt/dc01 && sudo umount /mnt/ewf_dc01
Volatility 3 (memory — rd01)
VOL="python3 /opt/volatility3-2.20.0/vol.py"
IMG="/cases/memory/rd01-memory.img"
# Human-readable process tree
$VOL -f $IMG -r pretty windows.pstree | cut -d '|' -f 1-11
# All processes incl. exited
$VOL -f $IMG windows.psscan | grep -v "N/A"
# Command lines
$VOL -f $IMG windows.cmdline | tee ./exports/cmdline.txt
# Process SIDs
$VOL -f $IMG windows.getsids | tee ./exports/getsids.txt
# Network connections
$VOL -f $IMG -r csv windows.netstat | tee ./exports/netstat.csv
# DLL list for a specific PID
$VOL -f $IMG -r csv windows.dlllist --pid 1912 | tee ./exports/dlllist-stun.csv
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.
- 4d ago First seen · 269 lines · 3,807 tokens per session scan B 5020a6e3a144
verisift CLAUDE.md is an instructions file published in the GitHub repository Zenidp/verisift (0 stars, last pushed 2mo ago), licensed MIT. It adds 3,807 tokens to every session, about $0.0190 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.