OpenParable
Skip to content
← Back to skills

Scan

Testing & Quality
scan

Scan is an Agent Skill for testing & quality published in the x-cmd/x-cmd repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Quick greedy scan for critical violations. Triggered by "/scan [target]" to find the top 1-5 most severe issues and stop early.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/x-cmd/x-cmd/blob/HEAD/mod/slash/lib/preset/scan/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/scan, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Quick Scanner

Trigger

Use when:

  • User says /scan
  • User wants a quick health check
  • Time-constrained review needed

Do NOT use when:

  • User wants exhaustive check (use /check)
  • User wants full assessment (use /assess)

Steps

Step 1: Parse Arguments

/scan [--ruleset <dir>] [target_root]

Default: current directory.

Step 2: Load Rules

x rule which
ls $ruleset_dir/*.yml
cat $ruleset_dir/*.yml

Step 3: Greedy Scan

Strategy:

  • Do NOT check every file against every rule
  • Find the 1-5 most obvious, most severe violations
  • Trust first instinct
  • Speed over completeness
  • Stop early when 1-5 critical issues found

Step 4: Output Results

Output Format

TSV with header:

root    target    ruleid    score    hint

If nothing obviously wrong: output header row only.

Constraints

  • Maximum 5 issues reported
  • Stop after finding 5 or when no obvious issues remain
  • Do NOT do exhaustive analysis