nlpm

Check cross-component consistency — reference integrity, orphans, contradictions

Auto-fix fixable issues in NL artifacts — missing fields, heading gaps, field renames

Initialize NLPM for this project — detect artifacts, set lint strictness, capture baseline trend snapshot

Discover and inventory all natural language programming artifacts in a repository

Render a self-contained HTML report — per-file scores, score trend, cross-component graph, vocabulary noun-verb map, drift candidates, and findings — into .claude/nlpm-reports/. Opens directly via file://. No server, no build, no network.

Cross-component consistency analyzer for NL programming artifacts. Checks reference integrity, detects orphans, finds behavioral contradictions, and identifies terminology drift across plugin components. <example> Context: User runs /nlpm:check on a plugin directory user: "/nlpm:check" assistant: "I'll use the checker to verify cross-component consistency." </example> <example> Context: Developer renamed a skill directory and wants to verify no broken references assistant: "I'll dispatch the checker to find any broken skill references across agents and commands." </example>

Discover and classify all NL programming artifacts in a repository. <example> Context: User wants to inventory their NL artifacts user: "/nlpm:scan" assistant: "I'll use the scanner to discover all NL artifacts." </example> <example> Context: User wants to check a specific project user: "/nlpm:scan ~/github/myproject" assistant: "I'll scan that project for NL programming artifacts." </example>

Scores NL programming artifacts on a 100-point scale using deterministic penalties. Use this agent when scoring plugin components, checking artifact quality, or running quality analysis on commands, agents, skills, rules, hooks, or CLAUDE.md. <example> Context: User runs /nlpm:score on a directory assistant: "I'll use the scorer to analyze and score these artifacts." </example> <example> Context: Quality check before a plugin release assistant: "I'll dispatch the scorer to verify all artifacts meet the threshold." </example> <example> Context: Fix command needs to identify issues before applying repairs assistant: "I'll use the scorer to identify issues and their penalties." </example>

Scan NL programming plugins (Claude Code, Codex CLI, Antigravity) for security risks in executable artifacts: hooks, scripts, MCP configs, dependencies, and prompt injection surfaces. Recognizes per-tool layouts — `.claude/`, `.codex/`, `.gemini/` / `.agent/` — and per-tool config formats (JSON for Claude/Gemini hooks, TOML for Codex `config.toml`). <example> Context: Auditing an external plugin before submitting PRs user: "Scan this plugin for security issues" assistant: "I'll use the security-scanner agent to check all executable artifacts." <commentary> Pre-contribution security gate. Must pass before any PRs are submitted to external repos. </commentary> </example> <example> Context: User wants to vet a plugin before installing user: "Is this plugin safe to install?" assistant: "I'll use the security-scanner agent to check for dangerous patterns." <commentary> Safety check for plugin consumers. Reports execution surfaces and risk level. </commentary> </example>

Researches one tool's CURRENT official documentation and diffs it against an nlpm convention overlay, returning a structured gap report (ADD / FIX / REMOVE / CONFIRM / RESOLVED) so the overlay can be brought up to date. Read-only on both the web and the repo — it never edits nlpm files. Use when an overlay (conventions-claude, conventions-codex, conventions-antigravity) may have drifted from the upstream spec it documents. <example> Context: User runs /nlpm:spec-sync to refresh the Claude Code overlay user: "/nlpm:spec-sync claude" assistant: "I'll dispatch the spec-researcher on the conventions-claude overlay to fetch the current Claude Code docs and report what changed." </example> <example> Context: A new Codex CLI release shipped and the overlay's changes table stops months ago user: "Has the Codex overlay fallen behind the latest releases?" assistant: "I'll use the spec-researcher to pull the latest Codex docs and GitHub releases and diff them against conventions-codex." </example> <example> Context: Maintainer wants to verify the overlays before a release without editing anything user: "Check the overlays for drift before I cut the release, but don't change anything." assistant: "I'll dispatch the spec-researcher in report-only mode for each overlay to surface stale field names and resolved uncertainties." </example>

Use when scoring or writing Antigravity (or legacy Gemini CLI) artifacts — covers .gemini/ paths, .agent/ workspace skills, gemini-extension.json, GEMINI.md, TOML slash commands, Gemini-lineage hook events. Spec is unsettled (Antigravity 2.0 launched 2026-05-19); many checks are advisory until PR-B verification.

Use when scoring or writing Claude Code artifacts — covers .claude/ paths, plugin.json schema, command + agent + skill frontmatter, CLAUDE.md, hook events, hooks.json format, settings.json, LSP, monitors, memory file conventions, and the Claude Code built-in tool catalog. Refreshed 2026-06-07 against docs map dated 2026-06-05 (Claude Code ≥ v2.1.16x).

Use when scoring or writing Codex CLI artifacts — covers .codex/config.toml schema, .codex-plugin/plugin.json, .agents/skills/ layout, Codex hook events, AGENTS.md hierarchy, marketplace.json, and the agents/openai.yaml sidecar. Refreshed 2026-06-07 against Codex 0.137.0 (2026-06-04).

Universal NL programming conventions — SKILL.md open spec (agentskills.io), AGENTS.md as canonical universal memory file, vague-quantifier list, prompt engineering layers, naming conventions, the override system. Tool-specific schemas live in nlpm:conventions-claude / nlpm:conventions-codex / nlpm:conventions-antigravity.

Multi-agent workflow patterns for Claude Code -- parallel dispatch, sequential pipelines, QC gates, retry loops, shared partials. Use when designing systems with multiple agents, commands, or processing stages.

1 hook across 1 event