Agent
Cross-artifact consistency checker for NL programming artifacts. Checks reference integrity, detects orphans, finds behavioral contradictions, and identifies terminology drift across plugin artifacts. Context: User runs /nlpm:check on a plugin directory user: "/nlpm:check" assistant: "I'll dispatch the checker for…
Agent
Discover and classify all NL programming artifacts in a repository. Context: User wants to see all their NL artifacts user: "/nlpm:ls" assistant: "I'll use the scanner to discover all NL artifacts." Context: User wants to check a specific project user: "/nlpm:ls /github/myproject" assistant: "I'll scan that project…
Agent
Scores NL programming artifacts on a 100-point scale using deterministic penalties. Use this agent when scoring plugin artifacts, checking artifact quality, or scoring commands, agents, skills, rules, hooks, or CLAUDE.md files. Context: User runs /nlpm:score on a directory assistant: "I'll use the scorer to score…
Agent
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…
Agent
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…
Agent
Evaluate NL artifacts against test specifications. Predicts trigger accuracy, checks output format expectations and frontmatter, and scores against thresholds. Context: Developer wrote a spec for a new agent and wants to check if it passes user: "/nlpm:test" assistant: "I'll use the tester to evaluate your artifacts…
Agent
Mechanical scanner for vague quantifier words in NL artifacts. Counts occurrences of flagged words and reports exact locations. Use this agent for fast, deterministic vague-word counting before the scorer applies judgment. Context: Score command dispatches vague-scanner in parallel with scorer assistant: "I'll scan…
Agent
Scans NL programming artifacts for vocabulary drift — same concept named differently across files — without requiring a declared canonical/deprecated registry. Output is advisory (judgment-based clustering, no penalty applied). Use when a project wants vocabulary feedback before adopting R51, or as a periodic health…
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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 2026-08-02 against current docs…
Skill Claude CodeCodex
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 2026-08-02 against Codex 0.146.0 (2026-07-29).
Skill Claude CodeCodex
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 /…
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
Use when writing or reviewing NL artifacts and need to check for anti-patterns — vague quantifiers, prohibitions without alternatives, oversized skills, write-on-read-only agents, monolithic prompts, or linter-duplicating rules.
Skill Claude CodeCodex
The 50 rules of natural language programming. Loaded when writing, reviewing, or improving any NL artifact — skills, agents, commands, rules, hooks, prompts, plugins, and the project memory file (CLAUDE.md / AGENTS.md / GEMINI.md). The definitive style guide for NL code quality.
Skill Claude CodeCodex
Use when scoring NL artifact quality, applying penalties, or calibrating lint judgment — contains the 100-point rubric with penalty tables per artifact type. Four worked calibration examples (Excellent Agent / Rewrite Agent / Excellent Rule / Weak Rule) live in references/calibration-examples.md, loaded on demand when…
Skill Claude CodeCodex
Detects execution surface risks, supply chain vulnerabilities, data exfiltration vectors, and prompt injection patterns in Claude Code plugins. Use when auditing plugins for security risks, reviewing MCP server configurations, scanning hooks and scripts for vulnerabilities, or checking extensions before installation.
Skill Claude CodeCodex
Use when writing test specs for NL artifacts, running /nlpm:test, or setting up TDD workflows for skills, agents, commands, rules, hooks, and prompts.
Skill Claude CodeCodex
Use when writing, reviewing, or naming any NLPM artifact (command, agent, skill, rule, workflow) — pick the canonical noun or verb from this registry rather than coining a synonym. Loaded by the scorer and checker agents to detect vocabulary drift across artifacts.
Skill Claude CodeCodex
How to write Claude Code agents that trigger reliably, use the right model, and produce consistent output. Use when creating, improving, or reviewing agent definitions.
Skill Claude CodeCodex
How to write Claude Code hooks -- event selection, hook types, matcher patterns, blocking vs advisory, portable paths. Use when creating hooks for quality gates, automation, or policy enforcement.
Skill Claude CodeCodex
How to design and build plugins -- architecture decisions, artifact selection, file structure, manifest configuration, marketplace publishing. Primarily Claude Code (.claude-plugin/plugin.json); the same architecture maps to Codex CLI (.codex-plugin/plugin.json) and Antigravity extensions. Use when planning, creating…
Skill Claude CodeCodex
How to write effective system prompts for any LLM. Universal prompt engineering -- role clarity, structured output, injection resistance, few-shot examples. Use when writing prompts, system instructions, or AI configuration.
Skill Claude CodeCodex
How to write .claude/rules/ files that Claude actually follows. Use when creating, improving, or reviewing project rules.