Public AGENTS.md

A repository-wide instruction file for TazWake/Public, a collection of defensive-security and digital-forensics tools, scripts, notes, and training environments. It explains the repository's purpose, supported environments, and contribution practices.

In plain words
What is it for?
Use it when modifying tools in the repository to follow its security scope, read the relevant documentation, use the correct shell environment, and document usage, dependencies, privileges, outputs, and safety concerns.
Why use it?
It helps coding agents make focused, safer changes while respecting the repository's Windows, WSL2, and Docker setup. It also requires documentation and input validation for new or changed tools.

Instructions file for CodexOpenCode

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 instructions/tazwake/public/agents-md
Clone the repo
git clone --depth 1 https://github.com/TazWake/Public

Made for: Codex, OpenCode.

Per session 333 This file is loaded in full into every session.
When invoked 333 The same file — it is already loaded in full.
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 $0.00333 $0.00333
Opus 5 $0.00167 $0.00167
Sonnet 5 $0.00067 $0.00067
Haiku 4.5 $0.00033 $0.00033

Measured 2d ago against content hash 25779a65bd92, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Public AGENTS.md 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 2d 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.

AGENTS.md · 23 lines

What it actually says

AGENTS.md

Guidance for coding agents working in D:\Development\Public.

Repository purpose

This is a public collection of tools, scripts, plugins, notes, notebooks, and containerized labs for incident responders, investigators, and other security professionals. It includes evidence collection and analysis utilities, Volatility plugins, synthetic evidence generators, and isolated training environments. All content is intended for authorized defensive security, forensic analysis, research, and education.

Working conventions

  • The host is Windows with PowerShell; run bash-only tooling through WSL2 or Docker.
  • Read the relevant directory README before changing a tool. Consult README.md and CLAUDE.md for broader context and Bash conventions.
  • Prefer small, focused changes and preserve established styles across Bash, PowerShell, Python, Go, C/C++, Lisp, notebooks, and container configuration.
  • Use rg for search. In PowerShell, redirect to $null, never nul.
  • New or changed tools should document their purpose, usage, dependencies, privileges, outputs, and important safety considerations.
  • Validate inputs, quote paths and shell variables, provide actionable errors, and retain forensic logging and integrity checks where applicable.
  • Test changes with the narrowest relevant check; use WSL2 or an isolated container for Linux-specific or potentially risky tooling.

Safety

  • Do not run destructive, collection, malware-analysis, scanning, rootkit, or attack-range tooling without explicit authorization and an appropriate isolated target.
  • Do not modify files outside this repository without approval, and do not commit generated evidence, case data, credentials, secrets, or large build artifacts.
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. 2d ago First seen · 23 lines · 333 tokens per session scan A 25779a65bd92

Subscribe to this mod's changes

Public AGENTS.md is an instructions file published in the GitHub repository TazWake/Public (44 stars, last pushed 13d ago), licensed CC0-1.0. It adds 333 tokens to every session, about $0.0017 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.