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/juwon1405/agentic-dart/claude-mdgit clone --depth 1 https://github.com/Juwon1405/agentic-dartWrote 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/juwon1405/agentic-dart/claude-md)<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>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 | $0.01506 | $0.01506 |
| Opus 5 | $0.00753 | $0.00753 |
| Sonnet 5 | $0.00301 | $0.00301 |
| Haiku 4.5 | $0.00151 | $0.00151 |
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.
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
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 · 122 lines · 1,506 tokens per session scan A 37fdfe179bac
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.
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.
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).
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.
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.
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.
sentry-selfhosted-mcp CLAUDE.md
Instructions for HieuAnh87/sentry-selfhosted-mcp, covering selfhosted-sentry-mcp — claude code overrides, claude-specific and quick reminders.