Skip to content
Back to skills

Engagement Intake And Planning

ASecurity

Ingest authorized engagement scope, validate targets and windows, and compile reviewable immutable action plans.

  • 2 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added October 15, 2026
securitypythonbashapi

Works with

  • cli
  • api

Security analysis

A100/100

Scanned October 15, 2026

npx -y skills add sodejm/copilot-operation-plugin-for-security --skill engagement-intake-and-planning --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Engagement Intake And Planning?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Engagement Intake And Planning
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/sodejm-engagement-intake-and-planning-copilot-operation-plugin-for-s/badge)](https://www.skillsdirectory.com/skills/sodejm-engagement-intake-and-planning-copilot-operation-plugin-for-s)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: engagement-intake-and-planning
description: Ingest authorized engagement scope, validate targets and windows, and compile reviewable immutable action plans.
---

# Engagement intake and execution planning

1. **Intake and RoE Verification**:
   - Collect and validate assessment targets, exclusions, operator ownership, assessment window, allowed effects, budget, and credential references.
   - Refuse any request lacking explicit operator identity, valid future assessment window, or unambiguous target specifications.

2. **Scope Boundary Enforcement**:
   - Reject wildcards (`*`, universal ranges), malformed network representations, and collisions where a target is simultaneously included and excluded.
   - Restrict active live requests to bounded subnets (/24 or narrower).

3. **Execution Mode Distinction**:
   - Explicitly distinguish between:
     - `planning`: Purely offline hypothesis modeling and test plan assembly.
     - `import`: Static parsing and ingestion of external logs, scans, and manifests.
     - `laboratory`: Synthetic or containerized simulation in an isolated environment.
     - `live`: Active network verification against production or staging infrastructure.
   - For `live` mode, mandate explicit budgets, non-empty emergency contacts, and active windows; refuse incomplete live requests.

4. **Action Plan Compilation**:
   - Produce an immutable `ActionPlan` (`cops.action-plan/v1`) with:
     - Declared platform prerequisites (OS, container boundaries, required CLI tools).
     - Bounded operations with an exact, independently measured caller-supplied tool version, expected evidence receipts, anticipated side effects, and cleanup obligations.
     - Execution budget limits and credential references.
     - Canonical SHA-256 `plan_digest`.
   - Do not infer or discover executable versions at runtime. Reject a missing or blank version for the scenario operation tool.

5. **CLI Invocation**:
   ```bash
   python3 -m cops engagement create --name "Scope Review" --owner "operator" --targets "10.0.0.5" --start "2026-10-05T00:00:00Z" --until "2026-10-05T23:59:59Z"
   python3 -m cops engagement validate <path-to-engagement.json>
   python3 -m cops engagement plan --engagement <path-to-engagement.json> --scenario COPS-E03.01-S01 --target 10.0.0.5 --tool-version python3=3.11.9
   ```

   Repeat `--tool-version TOOL=VERSION` when supplying more than one independently measured value. The CLI rejects malformed or blank entries and conflicting repeated values for the same tool. API callers must pass the required `tool_versions` mapping explicitly.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.