check
Check cross-artifact consistency — reference integrity, orphans, contradictions
Discover all natural language programming artifacts in a repository
> /plugin marketplace add xiaolai/nlpm > /plugin install nlpm@xiaolai
How it fires
How this command gets triggered: by you, by Claude, or both.
/lsContext preview
What this command does when you run it.
Discover all natural language programming artifacts in a repository
name: ls description: "Discover all natural language programming artifacts in a repository" argument-hint: "[repo-path]" allowed-tools: Read, Glob, Grep, Task
$ARGUMENTS
| Input | Path | |-------|------| | (empty) | current working directory | | directory path | use that path | | file path | ERROR: "Expected a directory. Use /nlpm:score for individual files." | | nonexistent path | ERROR: "Directory not found: {path}" |
Dispatch the `nlpm:scanner` agent with the target directory. The scanner follows the discovery patterns from `${CLAUDE_PLUGIN_ROOT}/commands/shared/discover.md` to discover all Category A (plugin) and Category B (project config) artifacts.
Print the scanner's report verbatim, using the exact structure defined in `${CLAUDE_PLUGIN_ROOT}/agents/scanner.md` (Output Format): the Category A (plugin) and Category B (project config) tables listing each artifact's path, line count, and token count, followed by the Total line. If no artifacts found: "No NL programming artifacts found in {path}."
Natural-Language Programming Manager — score, check, fix, and test NL artifacts across Claude Code, Codex CLI, and Antigravity. Tier-aware scoring with per-tool overlays. Part of the xiaolai plugin marketplace.
Check cross-artifact consistency — reference integrity, orphans, contradictions
Auto-fix fixable findings in NL artifacts — missing fields, heading gaps, field renames
Prepare NLPM for this project — detect artifacts, set strictness, capture baseline trend snapshot
Render a self-contained HTML report — per-file scores, score trend, cross-artifact graph, vocabulary noun-verb map, drift…
Score NL programming artifacts — 100-point quality score per file
Scan a Claude Code plugin for security risks in executable artifacts (hooks, scripts, MCP configs, dependencies).