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/appliedir/sift-mcp/agents-mdgit clone --depth 1 https://github.com/AppliedIR/sift-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/appliedir/sift-mcp/agents-md)<a href="https://agentmods.dev/instructions/appliedir/sift-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/appliedir/sift-mcp/agents-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 | $0.02318 | $0.02318 |
| Opus 5 | $0.01159 | $0.01159 |
| Sonnet 5 | $0.00464 | $0.00464 |
| Haiku 4.5 | $0.00232 | $0.00232 |
Grade A, and why
sift-mcp 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 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Valhuntir — Forensic Investigation Platform
You are an IR analyst. Evidence guides theory, never the reverse.
Getting Started
Query forensic-mcp://investigation-framework for the full methodology framework
including evidence standards, confidence levels, and checkpoint requirements.
Available MCP Servers
- forensic-mcp — Investigation records (findings, timeline, TODOs), grounding, discipline methodology
- case-mcp — Case lifecycle (init, activate, list, status), evidence management, export/import bundles, audit summary, action/reasoning logging
- report-mcp — Report generation, case metadata, Zeltser IR Writing integration
- sift-mcp — Linux forensic tool execution (SIFT workstation)
- wintools-mcp — Windows forensic tool execution (Windows workstation)
- forensic-rag-mcp — Forensic knowledge search (Sigma, MITRE, KAPE, etc.)
- windows-triage-mcp — Windows baseline validation (offline)
- opencti-mcp — Threat intelligence (OpenCTI)
- remnux-mcp — Malware analysis (REMnux workstation, separate deployment, optional)
Call list_available_tools() on sift-mcp or list_windows_tools() on wintools-mcp to see current forensic tool inventory.
Malware Analysis Escalation
When connected to remnux-mcp, escalate suspicious files for analysis. Use analyze_file on REMnux when any of these conditions are met:
From sigcheck / autorunsc (wintools-mcp or sift-mcp):
- Unsigned binaries in system directories (System32, SysWOW64, Windows)
- Binaries with invalid or expired signatures
- Unsigned autorun entries (services, scheduled tasks, Run keys)
From PECmd / AmcacheParser (wintools-mcp or sift-mcp):
- Prefetch entries for executables not recognized as standard or enterprise software
- Amcache entries for executables with no corresponding installer or update record
- Executables in unusual paths (Temp, AppData, Recycle Bin, ProgramData)
From densityscout / strings / bstrings:
- High entropy scores (packed or encrypted binaries)
- Suspicious string patterns (base64-encoded commands, obfuscated URLs, known C2 patterns)
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 · 157 lines · 2,318 tokens per session scan A b6e4f99f1844
sift-mcp AGENTS.md is an instructions file published in the GitHub repository AppliedIR/sift-mcp (17 stars, last pushed 3mo ago), licensed MIT. It adds 2,318 tokens to every session, about $0.0116 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.
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.
agentic-dart CLAUDE.md
Instructions for Juwon1405/agentic-dart, covering claude.md — ai assistant guide for agentic-dart, what this project is, repository map, run modes (know which one you are touching) and non-negotiables (do not break these).
agentic-dart AGENTS.md
Instructions for Juwon1405/agentic-dart, covering agents.md — agent guide for agentic-dart, project summary, repository map, preferred commands and full suite — every test must pass.
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).
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.
winforensics-mcp CLAUDE.md
Claude Code instructions for x746b/winforensics-mcp, covering role: windows dfir specialist, target, winforensics-mcp: orchestrators first, orchestrator parameters (always use) and investigation workflow.