nlpm

Plugin nlpm in xiaolai/codex-marketplace. Commands read from the repo's manifest — 1 month ago.

Skills (17)

• conventions-antigravity

  Antigravity and Gemini CLI artifact schemas: .gemini/ paths, extensions, hooks.

• conventions-claude

  Claude Code artifact schemas: plugin.json, frontmatter, hooks, settings, tools.

• conventions-codex

  Codex CLI artifact schemas: config.toml, .codex-plugin, skills, hooks, AGENTS.md.

• conventions

  Universal NL conventions: SKILL.md open spec, AGENTS.md, vague quantifiers, naming.

• orchestration

  Multi-agent workflow patterns: parallel dispatch, pipelines, QC gates, retries.

• patterns

  NL artifact anti-patterns: vague quantifiers, bare prohibitions, oversized skills.

• rules

  The 50 NL programming rules (R01-R50) for skills, agents, commands, hooks, prompts.

• scoring

  100-point NL artifact rubric: penalty tables per artifact type, calibration cases.

• security

  Plugin security risks: hooks, scripts, MCP configs, supply chain, prompt injection.

• testing

  NL artifact test specs for /nlpm:test: spec format, TDD for skills and agents.

• vocabulary

  NLPM noun/verb registry (R51): pick the canonical term, detect vocabulary drift.

• writing-agents

  How to write Claude Code agents: example blocks, model choice, least-privilege tools.

• writing-hooks

  How to write Claude Code hooks: events, matchers, blocking vs advisory, paths.

• writing-plugins

  How to design plugins: architecture, artifact choice, manifests, marketplaces.

• writing-prompts

  How to write LLM system prompts: role, structured output, injection resistance.

• writing-rules

  How to write .claude/rules/ files: golden format, enforceability, budget, scope.

• writing-skills

  How to write SKILL.md files that trigger reliably, for any tool (open spec).

Slash commands (15)

• /nlpm:check

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

• /nlpm:fix

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

• /nlpm:init

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

• /nlpm:ls

  Discover all natural language programming artifacts in a repository

• /nlpm:report

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

• /nlpm:score

  Score NL programming artifacts — 100-point quality score per file

• /nlpm:security-scan

  Scan a Claude Code plugin for security risks in executable artifacts (hooks, scripts, MCP configs, dependencies).

• /nlpm:shared:append-history

  Shared partial: append a scoring snapshot to .claude/nlpm-history.json. Used by /nlpm:init, /nlpm:score, and /nlpm:trend so trend data accumulates without manual upkeep.

• /nlpm:shared:classify

  Shared partial: classify a file path to its NL artifact type — command, agent, skill, rule, hook-config, manifest, etc. Used by /nlpm:score, /nlpm:fix, /nlpm:test, and /nlpm:check.

• /nlpm:shared:discover

  Shared partial: discover NL programming artifact files in a directory by category (A: plugin, B: project config, F: memory). Used by /nlpm:ls, /nlpm:score, /nlpm:check, and /nlpm:trend.

• /nlpm:spec-sync

  Sync nlpm's convention overlays with the latest official Claude Code / Codex / Antigravity specs — research upstream docs, diff, apply corrections, propagate, check

• /nlpm:test

  Run NL artifact tests — evaluate artifacts against .nlpm-test/*.spec.md specifications (TDD for natural language programming)

• /nlpm:trend

  Show quality score trends over time — track improvements, detect degradation

• /nlpm:vocab-drift

  Find vocabulary drift in a corpus without a declared registry — judgment-based clustering of likely-synonymous nouns and verbs. Advisory only, no penalty. Use for early-stage projects or as a periodic health check before/alongside R51.

• /nlpm:vocab-init

  Create a vocabulary skill for the target project — detect layout, extract literary warrant from the corpus, seed canonical noun/verb tables, write the opt-in stub. Use to start adopting R51 vocabulary discipline in any Claude Code plugin or NL-artifact-heavy repo.

Subagents (8)

• checker

  Cross-artifact consistency checker for NL programming artifacts. Checks reference integrity, detects orphans, finds behavioral contradictions, and identifies terminology drift across plugin artifacts. Use after renaming or moving a skill, partial, or script to find references across agents and comma

• scanner

  Discover and classify all NL programming artifacts in a repository — the current directory or a given project path — with per-file line counts. Not for scoring artifacts or checking cross-artifact consistency; it only inventories them (the scorer and checker do those). <example> Context: User wants

• scorer

  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 — including a pre-release check that all artifacts meet the threshold, an

• security-scanner

  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

• spec-researcher

  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

• tester

  Evaluate NL artifacts against test specifications. Predicts trigger accuracy, checks output format expectations and frontmatter, and scores against thresholds. Covers TDD runs where the spec is written first: a missing artifact is reported RED. Not for scoring artifacts that have no .nlpm-test spec;

• vague-scanner

  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, or for a quick check of vague language in a single file. Not for judging whet

• vocab-drift-scanner

  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

Hooks (1)

• PostToolUse

  "${CLAUDE_PLUGIN_ROOT}/scripts/check-artifact.sh"

Similar plugins