dfir-overview

dfir-overview is a skill for Claude Code, Codex from PurpleAILAB/Decepticon. It costs 68 tokens per session (889 once invoked), scanned A, original, Apache-2.0.

A digital forensics guide for checking detection rules against memory dumps, event logs, disk images, and other evidence from computers.

In plain words
What is it for?
It is for examining Windows and Linux memory, building event timelines, mining Windows logs, and matching Sigma or YARA rules to collected evidence.
Why use it?
It helps verify that Sigma and YARA detection rules work on real forensic data instead of merely looking correct on paper.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit It is for examining Windows and Linux memory, building event timelines, mining Windows logs, and matching Sigma or YARA rules to collected evidence.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/purpleailab/decepticon/dfir
About the project

Decepticon is an autonomous red-team agent that coordinates AI agents, security tools, sandboxes, and supporting services for authorized cybersecurity assessments. Security researchers and red teams can run it through its Docker stack, cloud service, command-line interface, or Python SDK, with the catalogue entries representing its available skills.

PurpleAILAB/Decepticon · 5,491 stars · on GitHub · decepticon.red

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.

Any agent
npx skills add PurpleAILAB/Decepticon --skill dfir
Clone the repo
git clone --depth 1 https://github.com/PurpleAILAB/Decepticon

Made for: Claude Code, Codex.

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 dfir-overview

README.md
[![agentmods](https://agentmods.dev/badge/skills/purpleailab/decepticon/dfir/github.svg)](https://agentmods.dev/skills/purpleailab/decepticon/dfir)
Your own site
<a href="https://agentmods.dev/skills/purpleailab/decepticon/dfir"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/dfir/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.

agentmods 80×15 button for dfir-overview

Your own site · 80×15
<a href="https://agentmods.dev/skills/purpleailab/decepticon/dfir"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/dfir.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 889 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00068 $0.00889
Opus 5 $0.00034 $0.00445
Sonnet 5 $0.00014 $0.00178
Haiku 4.5 $0.00007 $0.00089

Measured 9d ago against content hash c66c8b0a5459, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

dfir-overview 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 9d 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.

packages/decepticon/decepticon/skills/standard/dfir/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forensicator / DFIR Skill Catalog

Decepticon emits attacks AND detection rules. This catalog feeds the detection rules back through real forensic artifacts to confirm they fire — closing the Offensive Vaccine loop on the operations side.

Playbooks

Inline technique reference — not separately loadable skills. The entries below are summarized here for direct use; there is no separate SKILL.md to open for each. Do NOT call the skill loader on them — apply the technique with your tools using this summary and the Workflow in this file.

Technique Use for
volatility-windows Volatility 3 Windows plugins: pslist, malfind, cmdline, netscan, dlllist, handles
volatility-linux Volatility 3 Linux: linux.pslist, linux.bash, linux.malfind
plaso-timeline psort + log2timeline; super-timeline construction; Sigma matchers on the timeline
sigma-cli-validation sigma-cli convert + match against captured event logs
yara-scan yara-x scan against memory dumps and disk images
event-log-mining Windows Event Log (.evtx) extraction + key event ID reference
etw-trace ETW provider triage; .etl file extraction
edr-validation Replay an attack against a target with Velociraptor / OSQuery active; capture artifacts

Loop closure workflow

  1. Run an offensive technique (e.g., dcsync from the ad-operator agent).
  2. Detector agent emits Sigma rule describing the expected detection pattern (event 4662 with right ControlAccessRights, etc.).
  3. Defender pushes the Sigma to the customer SIEM via sigma_to_splunk_savedsearch / sigma_to_sentinel_analyticrule / sigma_to_elastic_detection_rule.
  4. Forensicator validates by:
    • Collecting the event log from the DC at attack time.
    • Running sigma-cli convert --target sqlite and matching against the log file.
    • If the match count is 0 → detection rule has a bug. Iterate with Detector.
    • If match count is N → detection works. Record the validation evidence in the engagement knowledge graph.
  5. Patcher proposes the fix; Forensicator validates the patch doesn't break the detection (verify the rule still fires on attempted exploitation of the patched build).

Read the full file on GitHub · 76 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. 9d ago First seen · 76 lines · 68 tokens per session scan A c66c8b0a5459

Subscribe to this mod's changes

dfir-overview is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,491 stars, last pushed 13d ago), licensed Apache-2.0. It adds 68 tokens to every session and 889 once invoked, about $0.0003 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 2026-09-03.