A digital forensics and incident response workflow for examining computer evidence without changing the original files. It produces checked findings and a report with paths to the results.

Use it to investigate disks and other case evidence, verify findings, and prepare a reviewed forensic report.

It gives investigations a repeatable evidence trail and prevents limited evidence from being presented as proof that nothing happened.

How TimothyVang/verdict-dfir configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to TimothyVang/verdict-dfir. 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/TimothyVang/verdict-dfir/master/.claude/skills/verdict/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/TimothyVang/verdict-dfir

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/timothyvang/verdict-dfir/verdict/github.svg)](https://agentmods.dev/skills/timothyvang/verdict-dfir/verdict)

Your own site

<a href="https://agentmods.dev/skills/timothyvang/verdict-dfir/verdict"><img src="https://agentmods.dev/badge/skills/timothyvang/verdict-dfir/verdict/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/timothyvang/verdict-dfir/verdict"><img src="https://agentmods.dev/badge/skills/timothyvang/verdict-dfir/verdict.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,709 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00078	$0.01709
Opus 5.5	$0.00031	$0.00684
Sonnet 5.5	$0.00016	$0.00342
Haiku 4.5	$0.00008	$0.00171

Measured 1mo ago against content hash 8ae3ae502bb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verdict 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 1mo 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/skills/verdict/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VERDICT DFIR

Use this skill to run the public VERDICT workflow from Claude Code. It is a guided entrypoint over the repository scripts and MCP tools; it is not a second product path.

Safety Rules

Evidence is read-only. Never mutate source evidence, mounted evidence, or original Case files.
Every Finding must cite a current-case tool_call_id.
Run verify_finding for each Finding and record each verifier decision with pool_handoff before judge_findings consumes the Findings.
report_qa must be audited before manifest_finalize; a failed or missing report QA gate blocks customer-ready output and requires expert review.
Optional n8n, grounding, browser, dashboard, and memory sidecars are operator aids only. They are never evidence and never create Findings.
Do not assert attribution, actor identity, legal breach status, or business impact.
Do not inflate limited coverage to NO_EVIL, clean, cleared, no compromise, or proof of no evil.
Disk images are content-scoped: local Sleuth Kit/libewf or SIFT can extract supported artifacts for parsing; if mount/extract produces no supported artifacts, the raw image remains custody-only.
If the pipeline stops before case_open, no Verdict exists. Report the failing line instead of summarizing evidence.

Steps

1. Resolve Evidence

If the operator supplied a path, use that exact path. If no path was supplied, use scripts/verdict --watch and ask the operator to drop evidence into evidence/.

Do not choose between multiple unrelated evidence files silently.

2. Preflight And Setup

Run the setup helper first:

bash scripts/verdict-setup.sh

Read its output, especially:

FIND_EVIL_GUEST_IP=<ip>
SIFT_OK=<0|1>

This helper builds missing MCP servers through scripts/install.sh, checks optional n8n/grounding availability, and attempts SIFT VM discovery when possible. Missing optional automation is non-fatal. Missing core runtime dependencies must be reported plainly.

Read the full file on GitHub · 142 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.

1mo ago First seen · 142 lines · 78 tokens per session scan A 8ae3ae502bb2

Subscribe to this mod's changes

verdict is a skill published in the GitHub repository TimothyVang/verdict-dfir (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 78 tokens to every session and 1,709 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-04.

Claude Code Security ai-forensics dfir digital-forensics forensics human-in-the-loop

vhir-tool-reference

Which Valhuntir MCP tool or SIFT tool to use for a question, file, IOC or artifact, and the step-by-step workflows that combine them (IOC investigation, threat actor research, detection engineering, malware analysis, disk, memory, timeline and network). Use when choosing tools or planning a multi-step analysis.

AppliedIR/sift-mcp · 69 tokens

finding-skeptic

Use before calling recordfinding on forensic-mcp, to challenge a drafted forensic finding. An isolated skeptic re-runs the cited tools and tries to refute the observation and interpretation; the investigator then records the finding as upheld, revised, contested or withdrawn.

AppliedIR/sift-mcp · 57 tokens

vhir-ingest

How to start an investigation once the evidence is surveyed: which tools to run first, ingesting evidence into OpenSearch (triage packages, memory, delimited files) and querying it. Use after the evidence survey, before analysis, or when ingesting or querying indexed evidence.

AppliedIR/sift-mcp · 61 tokens

vhir-playbooks

Investigation playbooks: step-by-step procedures, each with its triggers, phases and MITRE techniques. Use when an investigation needs one of: Credential Access Investigation; Data Staging Investigation; DNS Anomaly Investigation; Email Compromise Investigation; Log Tampering Investigation; Malware Analysis…

AppliedIR/sift-mcp · 105 tokens

vhir-malware-escalation

When and how to send a suspicious file to REMnux for malware analysis, by what the other tools found (signatures, autoruns, prefetch, entropy, injection, YARA, network). Use when a file, process or binary looks suspicious.

AppliedIR/sift-mcp · 60 tokens

vhir-report-writing

Writing the investigation report with report-mcp: the report profiles, case metadata, the writing guidance to follow and saving the report. Use once findings are approved and a report is wanted.

AppliedIR/sift-mcp · 42 tokens

verdict-dfir: Skill for Claude Code