nlpm
Natural-Language Programming Manager that scores, checks, fixes, and tests NL artifacts across Claude/Codex/Antigravity.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for nlpm, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
A Claude Code plugin (nlpm) that lints natural-language programming artifacts — skills, agents, rules, prompts — with tier-aware scoring and per-tool overlays for Claude Code, Codex CLI, and Antigravity. Ships a standalone Python validator (bin/nlpm-check) usable in pre-commit and CI, so it carries a real scriptable checking surface over agent artifacts including hooks/MCP configs.
Key features and capabilities
- Tier-aware NL artifact scoring
- Per-tool overlays (Claude/Codex/Antigravity)
- Standalone Python validator for CI
Use cases
- Lint skills/agents/rules for quality
- Gate NL artifacts in CI pipelines