agentleFS
Sign inStart free
dRafaleDdRafaleD/cybersec-skills/skills/operations/lean-dfir/SKILL.md

lean-dfir

Skill2 starsChanged 56 days agoMITView on GitHub

Runs token-efficient authorized digital forensics and incident response for Cursor and Codex. Hashes evidence, summarizes logs, and keeps chain-of-custody notes without dumping images into context. Use when the user asks for DFIR, forensics, log timeline, evidence handling, or incident reconstruction on data they already have. Do not use to attack systems, bypass encryption, alter evidence, recover others' data without authorization, or paste disk or memory images into chat.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the user points at a disk/memory image, hash it and stop.

    line 28
  2. Distinctive:

    Do not modify evidence. Do not clear logs.

    line 49
  3. Distinctive:

    Do not bypass disk encryption, crack passwords, or dump credential stores for reuse.

    line 50
  4. Distinctive:

    Do not image or scan machines the user does not administer.

    line 51

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Lean DFIR

Authorized forensics on copies the user already collected. Hash, summarize, preserve. Do not attack, decrypt-bypass, or dump images.

Let SKILL_ROOT be the folder that contains this SKILL.md. Prefer python3; on Windows use py -3.

python3 "$SKILL_ROOT/scripts/lean_dfir.py" hash /path/to/evidence
python3 "$SKILL_ROOT/scripts/lean_dfir.py" logs /path/to/logs-dir
python3 "$SKILL_ROOT/scripts/lean_dfir.py" trim --chars 2500 path/to/tool.txt

If the user points at a disk/memory image, hash it and stop. Do not parse $MFT, hives, or RAM in this chat.

Mode

Default lean.

ModeBudget
leanhash + log summary; references/custody.md; ≤8 timeline rows
standard+ extra log dirs; ≤12 rows
deepstill no image dumps; ≤16 rows

Workflow

  1. Confirm authorization and that work is on a copy.
  2. Hash each evidence file before reading.
  3. Summarize text logs (logs). Hunt with rg on those logs; do not paste full files.
  4. Build a short timeline. Recommend containment the user can apply on systems they own.

Hard rules

  • Do not modify evidence. Do not clear logs. Do not teach anti-forensics.
  • Do not bypass disk encryption, crack passwords, or dump credential stores for reuse.
  • Do not image or scan machines the user does not administer.
  • Binary images: hash + size only. Point them at their existing lab tools.

Report template

## Lean-dfir (`<mode>`)

**Incident:** <one line> | **Evidence hashed:** <n files>

| Time | Host/source | What | Why it matters |
|------|-------------|------|----------------|
| ISO-8601 | log:line | one clause | one clause |

**Custody:** copies hashed; originals untouched
**Not done:** memory/disk parse, credential dump

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free