Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add xiaolai/nlpm --skill vocabularygit clone --depth 1 https://github.com/xiaolai/nlpmWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xiaolai/nlpm/vocabulary)<a href="https://agentmods.dev/skills/xiaolai/nlpm/vocabulary"><img src="https://agentmods.dev/badge/skills/xiaolai/nlpm/vocabulary/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xiaolai/nlpm/vocabulary"><img src="https://agentmods.dev/badge/skills/xiaolai/nlpm/vocabulary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.03999 |
| Opus 5 | $0.00028 | $0.01999 |
| Sonnet 5 | $0.00011 | $0.00800 |
| Haiku 4.5 | $0.00006 | $0.00400 |
Grade A, and why
vocabulary scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NLPM Domain Vocabulary
The canonical noun-and-verb set NLPM uses to name what it does. Every artifact name, command name, agent name, rule wording, and prose description should draw from this registry. Synonyms are flagged by
/nlpm:checkand penalized by/nlpm:score.Sister skill:
nlpm:conventionsholds upstream Claude Code framework terms (hook events, frontmatter fields, manifest keys). This skill holds NLPM-internal domain language. If a term is from Anthropic's docs, it belongs inconventions. If it is from NLPM's own corpus, it belongs here.
How this registry is built
Every term listed below has literary warrant — it appears in at least one NLPM artifact today, captured by analysis/scripts/extract-vocabulary.py. Re-run that script after adding or renaming artifacts; the freshest output lives at analysis/vocabulary-extract/summary.md. New terms enter the registry only after one of the four warrant types from analysis/vocabulary-design-principles.md (P6) is satisfied — literary warrant alone is the entry bar for terms already in use; new coinages need user, structural, or domain warrant.
Two scopes (P1)
NLPM has two declared scopes. A homonym across them is a boundary, not a collision.
| Scope | Lives in | What it operates on |
|---|---|---|
| internal | commands/, agents/, skills/, bin/, scripts/, project CLAUDE.md |
NLPM's own behavior — scoring, checking, fixing, testing, listing, trending NL artifacts in the current project. |
| auditor | .github/workflows/auditor-*.yml, auditor/ |
The self-evolution pipeline that audits external repos, opens contribution PRs, tracks outcomes, refines rules. |
A verb that appears in both scopes (scan, test, discover) carries the same identity criterion in both — these are sanctioned homonyms. A verb that appears in only one scope (audit, contribute, track in auditor; score, check, fix, ls, trend, init in internal) is scope-bound; using it in the other scope requires either renaming or declaring a second scope-specific definition.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 228 lines · 57 tokens per session scan A 9c92d6971ec1
vocabulary is a skill published in the GitHub repository xiaolai/nlpm (135 stars, last pushed today), licensed ISC. It adds 57 tokens to every session and 3,999 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…