agentleFS
RifteoRifteo/skills/engagement-handoff/SKILL.md

engagement-handoff

Skill37 starsChanged 5 months agoMITView on GitHub

Documents the current state of an active pentest engagement so the next agent session can continue without losing context, covering findings, coverage, next steps, and open threads. Trigger when the user says "handoff", "save progress", "pick this up next session", or "summarize the engagement", when the context window is getting long and work needs to continue in a fresh session, or at the end of a testing day or shift change.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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. Distinctive:

    Create a compact handoff document that captures exactly where the current engagement stands.

    line 13
  2. Distinctive:

    Do NOT generate a handoff document — respond normally — when:

    line 19
  3. Distinctive:

    No engagement context has been provided — a handoff requires real session content to capture

    line 23
  4. Very specific:

    Use the template in references/handoff-template.md.

    line 37
  5. Distinctive:

    Keep it under 100 lines — if it's longer, you're duplicating instead of referencing

    line 41
  6. Distinctive:

    Never include credentials, tokens, or sensitive evidence in the handoff file

    line 42
  7. Distinctive:

    If ENGAGEMENT.md exists, open the handoff with: "Continue from: see ENGAGEMENT.md for scope and target details"

    line 44

≈ “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

Engagement Handoff

Create a compact handoff document that captures exactly where the current engagement stands. A fresh agent session reading this file should be able to continue without asking any questions.

Reference existing artifacts (ENGAGEMENT.md, findings already written) rather than duplicating them.

When NOT to use

Do NOT generate a handoff document — respond normally — when:

  • The user is asking general questions about pentest methodology or documentation practices
  • The user has not described an active engagement or session with findings and coverage
  • The user is asking how to write a final pentest report (use pentest-report instead)
  • No engagement context has been provided — a handoff requires real session content to capture

Process

  1. Scan the session — review all findings identified, tools run, targets tested, and threads opened
  2. Check for ENGAGEMENT.md — if it exists, reference it; do not repeat scope/target info already there
  3. Capture findings — list each finding by title + severity; do not rewrite them in full
  4. Map coverage — what was tested, what was skipped, what was partially tested
  5. List open threads — suspected vulnerabilities not yet confirmed, areas that need deeper testing, follow-up requests
  6. Write next steps — ordered list of what to do first in the next session
  7. Save — write to HANDOFF.md in the current directory

Output Format

Use the template in references/handoff-template.md.

Rules

  • Keep it under 100 lines — if it's longer, you're duplicating instead of referencing
  • Never include credentials, tokens, or sensitive evidence in the handoff file
  • Next steps must be specific enough that the next agent can start without any additional context
  • If ENGAGEMENT.md exists, open the handoff with: "Continue from: see ENGAGEMENT.md for scope and target details"

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.