fix
Auto-fix fixable findings in NL artifacts — missing fields, heading gaps, field renames
Check cross-artifact consistency — reference integrity, orphans, contradictions
> /plugin marketplace add xiaolai/nlpm > /plugin install nlpm@xiaolai
How it fires
How this command gets triggered: by you, by Claude, or both.
/checkContext preview
What this command does when you run it.
Check cross-artifact consistency — reference integrity, orphans, contradictions
name: check description: "Check cross-artifact consistency — reference integrity, orphans, contradictions" argument-hint: "[path]" allowed-tools: Read, Glob, Grep, Task
$ARGUMENTS
Parse `$ARGUMENTS` for path (default: cwd). Use `${CLAUDE_PLUGIN_ROOT}/commands/shared/discover.md` to discover all Category A+B artifacts. Read every file.
If no artifacts found → "No NL programming artifacts found."
If fewer than 2 artifacts → "Cross-artifact check requires multiple artifacts. Use /nlpm:score for individual files."
Dispatch the `nlpm:checker` agent with ALL artifacts and the instruction to perform cross-artifact checks:
1. **Reference integrity**
2. **Orphaned artifacts**
3. **Behavioral contradictions**
4. **Terminology drift**
NLPM Cross-Artifact Check
Artifacts checked: {N}
Reference Integrity:
{N} references checked, {N} broken
{list broken references}
Orphaned Artifacts:
{N} orphans found
{list orphans}
Contradictions:
{N} found
{list contradictions with both sides}
Terminology:
{N} inconsistencies
{list}
Verdict: {CLEAN | {N} findings}**Error handling:**
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.
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
Discover all natural language programming artifacts in a repository
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).