A command-line grounding tool that checks claims against supplied source material. It can process one claim, a document's claims, or multiple documents listed in a sourcemap file.

Use it to extract claims, score them against source documents, and check claims written in different languages.

It helps separate statements supported by the sources from statements that are not. Claim extraction is heuristic, so the resulting list should be reviewed before checking.

grounding — Skill for Claude Code by stellarshenson

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add stellarshenson/claude-code-plugins

Claude Code

/plugin install document-processing

Made for: Claude Code.

Or install document-processing, the plugin that ships this one along with the rest of its 5 skills, 5 commands.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/stellarshenson/claude-code-plugins/grounding/github.svg)](https://agentmods.dev/skills/stellarshenson/claude-code-plugins/grounding)

Your own site

<a href="https://agentmods.dev/skills/stellarshenson/claude-code-plugins/grounding"><img src="https://agentmods.dev/badge/skills/stellarshenson/claude-code-plugins/grounding/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/stellarshenson/claude-code-plugins/grounding"><img src="https://agentmods.dev/badge/skills/stellarshenson/claude-code-plugins/grounding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 7,347 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00075	$0.07347
Opus 5.5	$0.00030	$0.02939
Sonnet 5.5	$0.00015	$0.01469
Haiku 4.5	$0.00007	$0.00735

Measured 1mo ago against content hash 25036e4591dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

grounding 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 1mo 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.

plugins/document-processing/skills/grounding/SKILL.md · 404 lines

How it starts

The opening of the file, as written. The whole thing — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grounding Skill

Default engine: lexical mode

The grounder runs a frozen-weight logistic (LexicalVerdict) over 13-18 signals selected by the effort tier. High is the default tier (18 features, includes MT cross-lingual via argos CTranslate2 int8). Per-layer thresholds (--threshold, --bm25-threshold) affect the cascade fallback path only; in lexical mode the verdict comes from the logistic. Semantic (--semantic) and NLI are opt-in extras, unchanged.

Effort tiers (CPU-only, no extra install required)

low - 13 features; fastest; no language detection; English-only
medium - 16 features; adds lingua language detection + WordNet antonym contradiction
high - 18 features; adds argos MT for cross-lingual claims (translates non-English claim to EN then recall-scores); default

Set via lexical_effort in config_document_processing.yaml or --effort CLI overlay.

Three-step grounding chain

Grounding a document = three-step chain, not just step 2:

extract-claims — enumerate load-bearing claims from document into claims.json (heuristic, lossy — review before grounding).
ground — score every claim against source(s) with lexical-mode CLI (frozen-weight logistic over 13-18 signals; + optional --semantic); read verdicts, apply verdict rules; write grounding-report.md.
check-consistency — check document against itself for divergences grounding structurally can't see (42 users here vs 50 users there; dev/test/staging vs dev/staging/prod); write consistency-report.md.

Document-grounding run produces both grounding-report.md and consistency-report.md. Single claim (no document) → run only step 2's single-claim form (document-processing ground). Many documents → validate runs whole chain per client. Always run the CLI - canonical operational grounder; generative interpretation only an on-top layer for semantic claims after CLI ran.

validate skill wraps this whole chain, adds tone/style/length/format compliance layer on top; process skill invokes this skill from its Verify & Ground phase; update skill calls it as its mandatory closing step.

Read the full file on GitHub · 404 lines

Changes

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.

1mo ago First seen · 404 lines · 75 tokens per session scan A 25036e4591dc

Subscribe to this mod's changes

grounding is a skill published in the GitHub repository stellarshenson/claude-code-plugins (4 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 7,347 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-05.

Research

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

microsoft/vscode · 72 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

component-fixtures

Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.