Scan
Testing & QualityscanScan 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.
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- 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