ai-dfir-toolkit: Instructions file for Claude Code

CLAUDE.md

ai-dfir-toolkit CLAUDE.md is an instructions file for Claude Code, Codex from depalmar/ai-dfir-toolkit. It costs 6,013 tokens per session, scanned A, original, Apache-2.0.

A project guide for a catalog of traces left by AI coding agents, local language-model tools, workflow engines, and MCP components. It explains what each trace can prove and how investigators should collect it.

In plain words
What is it for?
It guides validation scripts, technique checks, count generation, and the creation of machine-readable endpoint-artifact records.
Why use it?
It keeps forensic collection separate from misuse catalogs and requires checks for schema, confidence, and technique references before results are trusted.

Instructions file for Claude CodeCodex

Written for Codex and Claude Code: reads ~/.codex or $CODEX_HOME, but also the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

This is depalmar/ai-dfir-toolkit's own configuration. It tells Claude Code and Codex how to work on ai-dfir-toolkit 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 ai-dfir-toolkit configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is python ../collectors/gen_credential_targets.py # collector targets, also CI-gated.

Reuse

Borrowing it

Nothing to install: this file belongs to depalmar/ai-dfir-toolkit. 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/depalmar/ai-dfir-toolkit/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/depalmar/ai-dfir-toolkit

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-dfir-toolkit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/depalmar/ai-dfir-toolkit/claude-md.svg)](https://agentmods.dev/instructions/depalmar/ai-dfir-toolkit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/depalmar/ai-dfir-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/depalmar/ai-dfir-toolkit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,013 This file is loaded in full into every session.
When invoked 6,013 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.06013 $0.06013
Opus 5 $0.03007 $0.03007
Sonnet 5 $0.01203 $0.01203
Haiku 4.5 $0.00601 $0.00601

Measured 7d ago against content hash 89807c758821, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ai-dfir-toolkit CLAUDE.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 7d 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.

CLAUDE.md · 421 lines

How it starts

The opening of the file, as written. The whole thing — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project context

Read this before working in artifacts/. It exists so a session starts with the rules already loaded instead of rediscovering them.

What this is

artifacts/ is a machine-readable catalog of the endpoint traces left by AI coding agents, local LLM runtimes, agentic workflow engines, and MCP components. It answers: what did this tool leave on the host, what does that prove, and in what order do I collect it.

It is deliberately not a living-off-the-land abuse catalog. LOLBAS and LOLRMM answer "what can this be misused to do." This one is for the person doing the acquisition, which is why every artifact carries forensic_value and evidence_type, and every entry carries a collection block.

Commands

Run everything from artifacts/. On Windows use python, on macOS/Linux python3; the scripts themselves are cross-platform (pathlib throughout) and write LF endings on every platform so the generated feeds stay byte-identical.

python scripts/validate.py                    # schema + sigma + confidence gate
python scripts/validate_techniques.py         # ATLAS/ATT&CK ids exist (--refresh re-pins)
python scripts/readme_counts.py               # README Contents block (--check gates it)
python scripts/normalize.py                   # collapse vocabulary drift
python scripts/export.py                      # regenerate docs/api feeds
python scripts/export_forensicartifacts.py    # Plaso / GRR / Timesketch format
python scripts/export_kape.py                 # KAPE targets (--check validates, writes nothing)
python scripts/export_velociraptor.py         # Velociraptor artifacts (--check likewise)
python scripts/normalize_notes.py             # note style (--check reports, writes nothing)
python scripts/data_sources.py                # telemetry coverage (--check audits only)
python scripts/verify_host.py                 # check catalogued paths on THIS machine
python ../collectors/gen_credential_targets.py     # collector targets, also CI-gated
python scripts/build_site.py --check          # site data contract, writes nothing
python scripts/build_site.py                  # regenerate docs/site (CI does this)
python ../artifacts/scripts/validate_mappings.py   # run this one from the repo root
python ../skills/agent-artifact-catalog/scripts/new_entry.py "Tool Name"

Read the full file on GitHub · 421 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. 7d ago First seen · 421 lines · 6,013 tokens per session scan A 89807c758821

Subscribe to this mod's changes

ai-dfir-toolkit CLAUDE.md is an instructions file published in the GitHub repository depalmar/ai-dfir-toolkit (23 stars, last pushed 17d ago), licensed Apache-2.0. It adds 6,013 tokens to every session, about $0.0301 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 instructions, from other repositories

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens