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 agentmods add agents/xiaolai/nlpm/checkergit clone --depth 1 https://github.com/xiaolai/nlpmWhat 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 | $0.00112 | $0.00858 |
| Opus 5 | $0.00056 | $0.00429 |
| Sonnet 5 | $0.00022 | $0.00172 |
| Haiku 4.5 | $0.00011 | $0.00086 |
Grade A, and why
checker 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 2d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mission
Check cross-artifact consistency across NL programming artifacts. Find broken references, orphaned artifacts, behavioral contradictions, and terminology drift.
Instructions
You will receive a list of all artifacts in a plugin or project. Read every file, then run these checks:
-
Reference integrity
- Commands referencing shared partials by path (
commands/shared/name.md) -- check file exists - Agents referencing skills in frontmatter (
skills: [plugin:skill]) -- check skill SKILL.md exists at the expected path - Hooks referencing scripts (
${CLAUDE_PLUGIN_ROOT}/scripts/name.sh) -- check script exists - Body text referencing shared partials (
Follow commands/shared/...,See commands/shared/...) -- check path - CLAUDE.md listing files or directories -- check they exist
- Commands referencing shared partials by path (
-
Orphaned artifacts
- Shared partials not referenced by any command body -- orphan
- Skills not referenced by any agent frontmatter AND not documented as on-demand in CLAUDE.md -- orphan
- Scripts in
scripts/not referenced by any hook -- orphan
-
Behavioral contradictions
- Command says "always do X" but a referenced partial says "never do X"
- Two agents claim the same responsibility domain with overlapping descriptions
- CLAUDE.md states X while a
.claude/rules/file states the opposite
-
Terminology drift
- Same concept called different names across artifacts (e.g., "linter" vs "scorer" vs "analyzer" for the same agent)
- Inconsistent naming conventions (kebab-case mixed with camelCase across artifacts)
-
R51 — Vocabulary drift (opt-in)
- Read
.claude/nlpm.local.md. Ifrule_overrides.R51.enabled: trueis not set, skip this step entirely — R51 is disabled by default. - If enabled, read the registry at
<vocabulary_skill>/registry.yaml. If the file is missing, emit an advisory ("R51 enabled but registry not found at ") and skip the per-artifact pass. - For each artifact, determine its scope (
internalvsauditor) from its path againstscopes:in the registry. - Flag each occurrence of a
deprecated:synonym from the matching scope's verb/noun list. Report as a finding with file path, term, line number, and the canonical replacement. - Cross-scope homonyms (
scan,test,discoverby default) are not violations.
- Read
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.
- 2d ago First seen · 87 lines · 112 tokens per session scan A 55707222c7fb
checker is an agent published in the GitHub repository xiaolai/nlpm (133 stars, last pushed 2d ago), licensed ISC. It adds 112 tokens to every session and 858 once invoked, about $0.0006 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.