agentic-dart CLAUDE.md

agentic-dart CLAUDE.md is an instructions file for coding agents from Juwon1405/agentic-dart. It costs 1,506 tokens per session, scanned A, original, MIT.

A guide for AI assistants working on Agentic-DART, an automated digital-forensics and incident-response tool. It explains the project layout, ways to run it, and rules that must not be broken.

In plain words
What is it for?
Use it when investigating digital evidence, running Agentic-DART, or changing its forensic tools, audit logging, and reports.
Why use it?
It gives the assistant the project context and prevents it from guessing about changing counts or using the wrong operating mode.

Instructions file

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/juwon1405/agentic-dart/claude-md
Clone the repo
git clone --depth 1 https://github.com/Juwon1405/agentic-dart

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 agentic-dart CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/juwon1405/agentic-dart/claude-md.svg)](https://agentmods.dev/instructions/juwon1405/agentic-dart/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/juwon1405/agentic-dart/claude-md"><img src="https://agentmods.dev/badge/instructions/juwon1405/agentic-dart/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,506 This file is loaded in full into every session.
When invoked 1,506 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 $0.01506 $0.01506
Opus 5 $0.00753 $0.00753
Sonnet 5 $0.00301 $0.00301
Haiku 4.5 $0.00151 $0.00151

Measured 4d ago against content hash 37fdfe179bac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentic-dart 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 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.

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 · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — AI Assistant Guide for Agentic-DART

Guidance for Claude Code (and any AI assistant) working in this repository. Read this before editing. The rules in Non-negotiables are load-bearing: they are the product, not style preferences.

This file deliberately carries no hard-coded counts (tool / test / case / finding totals, or the version number). Those change every time we ship; pinning them here would contradict our own measure-don't-guess rule and add one more surface to keep in sync. For any live number, run the Verify block — it is the single source of truth.

What this project is

Agentic-DART is an autonomous DFIR (Digital Forensics & Incident Response) agent. A senior-analyst reasoning loop calls typed, read-only forensic tools over MCP, records every call in a SHA-256-chained audit log, and produces a findings report. The guardrails live in the architecture (a read-only MCP boundary), not in the prompt.

Stack:    Python 3.10+, MCP, Anthropic SDK (live mode only)
Surface:  two layers — native pure-Python forensic functions + SIFT-tool adapters
Modes:    deterministic (default) / live / dry-run
License:  MIT
Entry:    SANS FIND EVIL! 2026

Exact tool / test / case / finding counts and the current version are intentionally not pinned here — run Verify for live values, or read pyproject.toml / CHANGELOG.md for the version.

Repository map

dart_audit/      SHA-256-chained JSONL logger — tamper-evident audit of every MCP call
dart_mcp/        Custom MCP server — typed, read-only forensic functions (native + SIFT adapters)
dart_agent/      Iteration controller, hypothesis tracker, deterministic + live loops
dart_corr/       Cross-artifact correlation engine — DuckDB joins, contradiction flagging
dart_playbook/   Senior-analyst YAML playbooks — DATA, not a Python package
examples/        case-studies/{self-evaluation,external-evaluation}/case-NN/ (README+truth.json+evidence_root), demos
scripts/         install.sh, benchmark/, scripts/eval/demo.py, generate_realistic_evidence.py
tests/           the main pytest suite; dart_corr/tests/ holds the correlation-engine tests
docs/            architecture, accuracy report, case walkthroughs

Read the full file on GitHub · 122 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. 4d ago First seen · 122 lines · 1,506 tokens per session scan A 37fdfe179bac

Subscribe to this mod's changes

agentic-dart CLAUDE.md is an instructions file published in the GitHub repository Juwon1405/agentic-dart (9 stars, last pushed 2mo ago), licensed MIT. It adds 1,506 tokens to every session, about $0.0075 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 2026-08-31.

Related

Other instructions, from other repositories

ai-dfir-toolkit CLAUDE.md

Instructions for depalmar/ai-dfir-toolkit, covering project context, what this is, commands, rules that are not negotiable and what a restricted runner cannot verify.

depalmar/ai-dfir-toolkit · 6,013 tokens

SAVVYDFIR-MCP CLAUDE.md

Instructions for kismatkunwar89/SAVVYDFIR-MCP, covering savvydfir-mcp - dfir investigation framework, what this is, critical rules, forensic knowledge in tool responses and investigation workflow (7 phases).

kismatkunwar89/SAVVYDFIR-MCP · 10,844 tokens

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.

AppliedIR/sift-mcp · 2,318 tokens

mem_forensics-mcp CLAUDE.md

Claude Code instructions for x746b/mem_forensics-mcp, covering role: memory forensics specialist, mem-forensics-mcp: triage first, architecture, investigation questions -> tools and workflow.

x746b/mem_forensics-mcp · 1,224 tokens

sentry-selfhosted-mcp AGENTS.md

Instructions for HieuAnh87/sentry-selfhosted-mcp, covering selfhosted-sentry-mcp, commands, install deps, build typescript to ./build and set executable bit and watch mode during source edits.

HieuAnh87/sentry-selfhosted-mcp · 512 tokens

sentry-selfhosted-mcp CLAUDE.md

Instructions for HieuAnh87/sentry-selfhosted-mcp, covering selfhosted-sentry-mcp — claude code overrides, claude-specific and quick reminders.

HieuAnh87/sentry-selfhosted-mcp · 111 tokens