elastic-docs-skills: Agent for Claude Code

.github/agents/docs-freshness-checker.agent.md

docs-freshness-checker is an agent for Claude Code from elastic/elastic-docs-skills. It costs 31 tokens per session (1,135 once invoked), scanned A, original, Apache-2.0.

An agent that checks documentation-based skill files against their original online sources and updates them when the sources have changed.

In plain words
What is it for?
Use it to find skill files, read their source links, compare current source content, and refresh skills that have drifted.
Why use it?
It helps prevent skill instructions from becoming outdated as upstream documentation changes.

Agent for Claude Code ✓ vendor

Written for Claude Code: shipped in a Claude Code plugin.

This is elastic/elastic-docs-skills's own configuration. It tells Claude Code how to work on elastic-docs-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything elastic-docs-skills configures →

Part of the elastic-docs-skills plugin — 21 skills, 4 agents shipped together

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

Reuse

Borrowing it

Nothing to install: this file belongs to elastic/elastic-docs-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/elastic/elastic-docs-skills/main/.github/agents/docs-freshness-checker.agent.md
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, 4 agents.

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-freshness-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/elastic/elastic-docs-skills/docs-freshness-checker.svg)](https://agentmods.dev/agents/elastic/elastic-docs-skills/docs-freshness-checker)
Your own site
<a href="https://agentmods.dev/agents/elastic/elastic-docs-skills/docs-freshness-checker"><img src="https://agentmods.dev/badge/agents/elastic/elastic-docs-skills/docs-freshness-checker.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,135 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.01135
Opus 5 $0.00015 $0.00567
Sonnet 5 $0.00006 $0.00227
Haiku 4.5 $0.00003 $0.00113

Measured 6d ago against content hash 1c5b270317e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

docs-freshness-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 6d 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.

.github/agents/docs-freshness-checker.agent.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a freshness checker for the elastic-docs-skills catalog. Your job is to compare each skill file against its upstream source URLs and update skills that have drifted.

Finding skills and their sources

Skill files live at skills/**/SKILL.md. Each skill has a YAML frontmatter block and a Markdown body encoding rules, syntax, or workflows derived from upstream Elastic documentation.

Source URLs are declared in each skill's YAML frontmatter under the sources: field:

---
name: my-skill
sources:
  - https://www.elastic.co/docs/some-page
  - https://docs-v3-preview.elastic.dev/some/other/page
---

To find all skills and their sources:

  1. Find every SKILL.md file under the skills/ directory.
  2. Parse the YAML frontmatter of each file.
  3. Read the sources: list. If a skill has no sources: field, use the Elastic Docs MCP server to discover relevant upstream content (see "Skills without explicit sources" below).

How to check freshness

For each skill:

  1. Read the SKILL.md file completely
  2. Fetch upstream content:
    • If sources: exist: fetch each source URL (append .md to the URL for LLM-friendly versions)
    • If no sources:: use the Elastic Docs MCP server (https://www.elastic.co/docs/_mcp/) — call SemanticSearch with the skill's name and description to find relevant upstream pages, then fetch the top results with GetDocumentByUrl (with includeBody: true)
  3. Compare the fetched content against what the skill encodes:
    • Are all rules from the upstream source present in the skill?
    • Has any syntax changed (new options, renamed directives, changed defaults)?
    • Have any options, rules, or features been removed upstream?
    • Are there new sections or rules upstream that the skill doesn't cover?
  4. Classify the drift:
    • Meaningful drift: new rules added, syntax changed, options removed, behavior changed
    • Cosmetic drift: rewording, reordering, formatting changes that don't affect the substance
  5. Only update for meaningful drift. Ignore cosmetic drift.

Read the full file on GitHub · 117 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.

  1. 6d ago First seen · 117 lines · 31 tokens per session scan A 1c5b270317e9

Subscribe to this mod's changes

docs-freshness-checker is an agent published in the GitHub repository elastic/elastic-docs-skills (71 stars, last pushed 2d ago), licensed Apache-2.0. It adds 31 tokens to every session and 1,135 once invoked, about $0.0002 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.