Borrowing it
Nothing to install: this file belongs to kismatkunwar89/SAVVYDFIR-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kismatkunwar89/SAVVYDFIR-MCP/master/CLAUDE.mdgit clone --depth 1 https://github.com/kismatkunwar89/SAVVYDFIR-MCPWrote 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/kismatkunwar89/savvydfir-mcp/claude-md)<a href="https://agentmods.dev/instructions/kismatkunwar89/savvydfir-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kismatkunwar89/savvydfir-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/kismatkunwar89/savvydfir-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kismatkunwar89/savvydfir-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.10844 | $0.10844 |
| Opus 5 | $0.05422 | $0.05422 |
| Sonnet 5 | $0.02169 | $0.02169 |
| Haiku 4.5 | $0.01084 | $0.01084 |
Grade A, and why
SAVVYDFIR-MCP CLAUDE.md scanned grade A 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Blocked commands**: rm, dd, mkfs, shred, wget, curl, ssh, scp, fdisk, parted, nc How it starts
The opening of the file, as written. The whole thing — 758 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAVVYDFIR-MCP - DFIR Investigation Framework
What This Is
AI-driven Digital Forensics & Incident Response on SANS SIFT Workstation. You are the investigator. All evidence is READ-ONLY. Chain of custody applies.
Critical Rules
- NEVER write to
/evidence/or/mnt/- read-only evidence and mount paths - Write output ONLY to
analysis/,reports/,/cases/, or/tmp/- RBAC-enforced in server.py - Every finding must cite: artifact path + exact command + timestamp
- Load skills on-demand - do not preload all skills at once
- Case-agnostic: no hardcoded IPs, usernames, or filenames - universal patterns only
Forensic Knowledge in Tool Responses
Every tool response now carries forensic_caveat, corroborate_with, and discipline_reminder injected from in-house forensic-knowledge YAMLs at the point of interpretation. Read these fields - they tell you what this artifact does NOT prove and what to run next. CLAUDE.md is for investigation structure. Tool responses carry the artifact-specific rules.
Investigation Workflow (7 Phases)
PHASE 1: Volatile Data - Memory First (5-10 min)
Run ALL in one batch (parallel-safe):
list_processes(case_id)
scan_processes(case_id)
detect_injection(case_id) ← MANDATORY
scan_network(case_id) ← captures every active socket
list_dlls(case_id, pid) ← MANDATORY for each PID from scan_network
load_memory(memory_image_path)
PHASE 2: Triage Baseline - Disk Artifacts (15-30 min)
Run dotnet tools SEQUENTIALLY - never parallel (saturates 4 vCPU):
mount_image
extract_mft_timeline(case_id)
extract_usn_journal(case_id) ← do NOT delay - USN rolls over
summarize_evtx(case_id) ← 2-stage: channel inventory + extraction
extract_prefetch(case_id)
get_amcache(case_id)
extract_shimcache(mount_point, case_id)
extract_registry_run_keys(case_id)
extract_srum(mount_point, case_id)
extract_shellbags(image_path, case_id) ← per-profile Explorer folder navigation (SBECmd)
extract_lnk_files(image_path, case_id) ← per-profile Recent LNK shortcuts (LECmd)
extract_jump_lists(image_path, case_id) ← per-profile Jump Lists / AppId-to-file (JLECmd)
extract_browser_history(image_path, case_id) ← Chrome/Edge/Firefox visits+downloads (native sqlite3)
extract_registry_fileaccess(image_path, case_id) ← UserAssist/RecentDocs/OpenSavePidlMRU/TypedPaths (hybrid RECmd)
extract_recycle_bin(image_path, case_id) ← per-SID $Recycle.Bin/$I deleted-file metadata (native $I parser)
extract_powershell_history(image_path, case_id) ← per-profile ConsoleHost_history.txt PowerShell commands
extract_scheduled_tasks(image_path, case_id) ← Windows\System32\Tasks scheduled-task XML (persistence)
extract_windows_artifacts(case_id) ← stage raw artifacts first when mount_image reports SleuthKit-direct access, OR when a parser returns needs_extract_windows_artifacts=true
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.
- 12d ago First seen · 758 lines · 10,844 tokens per session scan A 5dfc9e9917f6
SAVVYDFIR-MCP CLAUDE.md is an instructions file published in the GitHub repository kismatkunwar89/SAVVYDFIR-MCP (4 stars, last pushed 3mo ago), licensed MIT. It adds 10,844 tokens to every session, about $0.0542 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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.
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.
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.
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).
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.
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).