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/tazwake/public/claude-mdgit clone --depth 1 https://github.com/TazWake/PublicWrote 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/tazwake/public/claude-md)<a href="https://agentmods.dev/instructions/tazwake/public/claude-md"><img src="https://agentmods.dev/badge/instructions/tazwake/public/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 | $0.02612 | $0.02612 |
| Opus 5 | $0.01306 | $0.01306 |
| Sonnet 5 | $0.00522 | $0.00522 |
| Haiku 4.5 | $0.00261 | $0.00261 |
Grade B, and why
Public CLAUDE.md scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo D:\Development\Public\Bash\evidence_collector.sh /path/to/storage/device How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Overview
This is a comprehensive DFIR (Digital Forensics and Incident Response) tools repository containing production-ready forensic analysis scripts, containerized lab environments, and specialized plugins for memory analysis frameworks.
Environment Notes
- Host Environment: Windows with PowerShell (not Linux)
- WSL2 Access: Bash is available via WSL2 for Linux-specific commands
- CRITICAL: Avoid piping output to
nul- this creates a file in Windows that breaks git push and other commands. Use>$nullin PowerShell or>/dev/nullin WSL2/bash instead. - Container Development: Use Docker for Linux-specific testing and tools
- Cross-Platform Compatibility: Bash scripts are designed for Linux/macOS execution or WSL2
- Building: Request assistance for compilation if cross-platform issues occur
Code Best Practices
General Guidelines
- Always use descriptive variable names unless specifically asked to create obfuscated code
- If an instruction is unclear or impossible to complete without more information, ask questions
- Follow good practice designs for code and content unless directed otherwise
Bash Script Development
When writing or modifying bash scripts, follow these principles:
- Begin scripts with
set -euo pipefailfor strict error handling - Include help output and comments explaining the "why" behind implementation choices
- Use full absolute paths for commands (e.g.,
/usr/bin/nmapinstead ofnmap) - Always quote variables (e.g.,
"$variable") to prevent word splitting - Validate and sanitize all user input to prevent command injection
- Use functions for complex tasks with
localvariables to prevent namespace pollution - Include clear error messages that explain what went wrong and how to fix it
- Add logging for actions to support forensic analysis and auditing
- Run ShellCheck on critical scripts before deployment
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 · 245 lines · 2,612 tokens per session scan B 7120890ef8e4
Public CLAUDE.md is an instructions file published in the GitHub repository TazWake/Public (44 stars, last pushed 15d ago), licensed CC0-1.0. It adds 2,612 tokens to every session, about $0.0131 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 2026-08-30.
Other instructions, from other repositories
cs CLAUDE.md
Claude Code instructions for boyter/cs, covering claude.md, project overview, build & test commands, architecture and query pipeline (pkg/search/).
CheatSheetSeries CLAUDE.md
Claude Code instructions for OWASP/CheatSheetSeries, covering claude.md and for maintainers.
winforensics-mcp CLAUDE.md
Claude Code instructions for x746b/winforensics-mcp, covering role: windows dfir specialist, target, winforensics-mcp: orchestrators first, orchestrator parameters (always use) and investigation workflow.
q-code AGENTS.md
Instructions for v833/q-code, covering q-code 项目协作说明, 项目概览, 环境与工具, 常用命令 and cli 子命令.
gaia-ai CLAUDE.md
Claude Code instructions for alexey-max-fedorov/gaia-ai, covering what this repo is, routing rules, prompts/ — the product, website/ — commands and website architecture.
sift-mcp AGENTS.md
Instructions for AppliedIR/sift-mcp, covering valhuntir — forensic investigation platform, getting started, available mcp servers, malware analysis escalation and investigation recording.