docs-check-contradictions

docs-check-contradictions is a skill for Claude Code from elastic/elastic-docs-skills. It costs 75 tokens per session (2,955 once invoked), scanned A, original, Apache-2.0.

A documentation review tool that looks for contradictions between new or changed documentation and existing Elastic documentation.

In plain words
What is it for?
It is for checking documentation changes against files in the local project and published Elastic docs.
Why use it?
It helps prevent readers from finding conflicting instructions, names, settings, or recommendations in different places.

Skill for Claude Code ✓ vendor

Written for Claude Code: allowed-tools in frontmatter.

Part of the elastic-docs-skills plugin — 21 skills, 1 agent shipped together

Good fit It is for checking documentation changes against files in the local project and published Elastic docs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/elastic/elastic-docs-skills/check-contradictions
About the project

Elastic Docs Skills is a collection of Claude Code skills for creating and maintaining Elastic documentation. It is for developers and documentation contributors who use coding agents such as Claude Code, Cursor, or Codex. The catalogue entries are the project's reusable documentation workflows, agents, plugin, and instruction.

elastic/elastic-docs-skills · 71 stars · on GitHub · elastic.github.io

Install

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.

Any agent
npx skills add elastic/elastic-docs-skills --skill check-contradictions
Clone the repo
git clone --depth 1 https://github.com/elastic/elastic-docs-skills

Made for: Claude Code.

Or install elastic-docs-skills, the plugin that ships this one along with the rest of its 21 skills, 1 agent.

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.

agentmods badge for docs-check-contradictions

README.md
[![agentmods](https://agentmods.dev/badge/skills/elastic/elastic-docs-skills/check-contradictions/github.svg)](https://agentmods.dev/skills/elastic/elastic-docs-skills/check-contradictions)
Your own site
<a href="https://agentmods.dev/skills/elastic/elastic-docs-skills/check-contradictions"><img src="https://agentmods.dev/badge/skills/elastic/elastic-docs-skills/check-contradictions/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.

agentmods 80×15 button for docs-check-contradictions

Your own site · 80×15
<a href="https://agentmods.dev/skills/elastic/elastic-docs-skills/check-contradictions"><img src="https://agentmods.dev/badge/skills/elastic/elastic-docs-skills/check-contradictions.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 2,955 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00075 $0.02955
Opus 5 $0.00037 $0.01477
Sonnet 5 $0.00015 $0.00591
Haiku 4.5 $0.00007 $0.00296

Measured 10d ago against content hash 2a00ae2ce4d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

docs-check-contradictions 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 10d 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.

skills/review/check-contradictions/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a documentation consistency checker for Elastic. Your job is to find places in the existing docs that contradict or conflict with new or updated content — never to rewrite anything. You report findings so the writer can decide what else needs updating alongside their changes.

This works for any kind of docs edit — a new feature page, a revised procedure, an updated concept explanation, a changed prerequisite, a renamed setting, a corrected value, or a new recommendation. Do not assume the change is feature-related.

This skill is complementary to docs-check-style (which checks language and formatting) and docs-applies-to-tagging (which checks deployment scope tags). Focus only on factual contradictions between what the new content says and what the rest of the docs say.

Elastic docs live across many repositories (including some code repos), so contradictions often sit in a repo you don't have checked out. You therefore search in two places:

  1. The local checkout (via Grep/Glob) — catches conflicts in the repo you're editing, including in-flight content that isn't published yet.
  2. All published Elastic docs (via the Elastic Docs MCP server at https://www.elastic.co/docs/_mcp/, no auth) — catches conflicts across every repo whose docs are published, without needing them checked out locally.

If the Elastic Docs MCP server tools (search_docs, get_document_by_url, etc.) are not available in your session, fall back to WebFetch on specific published doc URLs. Note both approaches in your report. The MCP only sees published docs. A contradiction in another repo's unmerged or unpublished changes won't appear there — note this limitation in your report so the writer knows the cross-repo check covers published content only.

Inputs

$ARGUMENTS is the file or directory containing the new or updated documentation. If empty, ask the user which file or directory to check.

Read the full file on GitHub · 174 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 10d ago First seen · 174 lines · 75 tokens per session scan A 2a00ae2ce4d6

Subscribe to this mod's changes

docs-check-contradictions is a skill published in the GitHub repository elastic/elastic-docs-skills (71 stars, last pushed today), licensed Apache-2.0. It adds 75 tokens to every session and 2,955 once invoked, about $0.0004 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.