scope — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited scope (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Helps you thoroughly understand a problem space through codebase exploration and iterative dialogue, then creates a well-specified ticket for future implementation.
This skill does NOT write code. It explores, questions, understands, and documents.
Understand what the user wants to explore:
Ask clarifying questions:
Output: Clear understanding of what problem space to explore.
Use exploration tools to understand context:
Explore agent (set thoroughness based on scope: "quick", "medium", "very thorough")For third-party dependencies:
/tmp for examination if neededExploration goals:
Output: Comprehensive understanding of the relevant codebase areas.
Use AskUserQuestion to refine understanding:
Loop until both Claude and user have:
Important: This is collaborative design, not just requirements gathering. Challenge assumptions, propose alternatives, discuss trade-offs.
Output: Shared, precise understanding of the work to be done.
Draft ticket content adaptively based on type:
For feature proposals:
sec-blue-teamer agent if the implications are non-obvious.)For refactorings:
For complex bug fixes:
Format guidelines:
Output: Draft ticket content for user review.
Present draft to user:
Iterate if needed:
Output: Approved ticket content ready to create.
Detect the issue tracker and create the ticket per references/trackers.md (Detection Procedure + "Create" operation). Capture and present the resulting ticket URL.
Output: Created ticket with URL.
This skill will:
This skill will NOT:
Exploration thoroughness:
Ticket quality over speed:
Integration with /implement:
/scope creates the ticket, /implement implements it/scope can be handed to someone else or tackled later with /implement~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.