update-starlight-docs

update-starlight-docs is a skill for Claude Code, Codex from jmrplens/gitlab-mcp-server. It costs 44 tokens per session (850 once invoked), scanned A, original, MIT.

A documentation-maintenance workflow for Astro Starlight, a documentation site framework. It updates user-facing documentation when code changes affect features, configuration, deployment, or behavior, while also accounting for a separate contributor documentation set.

In plain words
What is it for?
Use it after adding tools, configuration options, capabilities, transport changes, error handling, security changes, or automatic-update behavior. It maps each change to pages such as the tools reference, configuration guide, troubleshooting, and security documentation.
Why use it?
It helps prevent the user documentation from falling behind the product. It also identifies the affected English and Spanish pages and requires related developer documentation to be updated.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/jmrplens/gitlab-mcp-server/update-starlight-docs
Any agent
npx skills add jmrplens/gitlab-mcp-server --skill update-starlight-docs
Clone the repo
git clone --depth 1 https://github.com/jmrplens/gitlab-mcp-server

Made for: Claude Code, Codex.

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 update-starlight-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/jmrplens/gitlab-mcp-server/update-starlight-docs.svg)](https://agentmods.dev/skills/jmrplens/gitlab-mcp-server/update-starlight-docs)
Your own site
<a href="https://agentmods.dev/skills/jmrplens/gitlab-mcp-server/update-starlight-docs"><img src="https://agentmods.dev/badge/skills/jmrplens/gitlab-mcp-server/update-starlight-docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 850 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 $0.00044 $0.00850
Opus 5 $0.00022 $0.00425
Sonnet 5 $0.00009 $0.00170
Haiku 4.5 $0.00004 $0.00085

Measured today against content hash d7157ed6a919, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update-starlight-docs 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 today.

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/skills/update-starlight-docs/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Starlight Documentation

Update the Astro Starlight user documentation site to reflect code changes that affect user-facing features, configuration, or behavior.

Before Starting

  1. Identify what changed in the code that affects users
  2. Read the current Starlight docs structure: site/src/content/docs/
  3. Determine affected pages (EN and ES)

Documentation Architecture

Two documentation systems coexist:

System Path Audience Format
Developer docs docs/ Contributors, AI agents Markdown
User docs site/src/content/docs/ End users MDX (Starlight)

Rule: Code changes that affect user-facing behavior MUST update BOTH systems.

Steps

1. Map code changes to affected docs

Code Change User Doc Pages
New MCP tool tools-reference, relevant domain page
New config option configuration, env-reference
New capability capabilities, getting-started
Transport change getting-started, http-server-mode
Error handling change troubleshooting, error-handling
Security change security

2. Edit EN pages first

All pages live under site/src/content/docs/en/:

site/src/content/docs/en/
├── index.mdx          # Landing page
├── getting-started.mdx
├── configuration.mdx
├── tools-reference.mdx
├── ...

3. Edit corresponding ES pages

Mirror structure under site/src/content/docs/es/ with translated content.

4. Frontmatter requirements

Every .mdx file must have:

---
title: "Page Title"
description: "Brief description for SEO and sidebar"
sidebar:
  order: 5  # Controls sidebar ordering
---

5. Use Starlight components

import { Aside, Tabs, TabItem, Card, CardGrid, Steps, FileTree, LinkCard } from '@astrojs/starlight/components';

<Aside type="tip">Helpful tip here</Aside>
<Aside type="caution">Warning message</Aside>
<Aside type="danger">Critical warning</Aside>

<Tabs>
  <TabItem label="Linux">Linux instructions</TabItem>
  <TabItem label="macOS">macOS instructions</TabItem>
  <TabItem label="Windows">Windows instructions</TabItem>
</Tabs>

<Steps>
1. First step
2. Second step
3. Third step
</Steps>

Read the full file on GitHub · 119 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. today Changed · -1 lines d7157ed6a919
  2. 4d ago First seen · 120 lines · 44 tokens per session scan A 375921eae18e

Subscribe to this mod's changes

update-starlight-docs is a skill published in the GitHub repository jmrplens/gitlab-mcp-server (33 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 850 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.

Related

Other skills, from other repositories

browser-use

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.

browser-use/browser-use · 26 tokens

open-source

Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…

browser-use/browser-use · 137 tokens

kayba-stage-5-action-plan

Triage each insight into discard/code-fix/prompt-fix and produce a prioritized action plan with specific recommendations. Trigger when the user says "run stage 5", "make action plan", "triage skills", or when invoked by the kayba-pipeline orchestrator. Requires eval outputs from stages 1-4.

kayba-ai/agentic-context-engine · 74 tokens

kayba-stage-2-domain-context

Gather domain context about the repository and agent — system prompt, tool definitions, domain docs, and behavior patterns from traces. Trigger when the user says "run stage 2", "gather context", "domain context", or when invoked by the kayba-pipeline orchestrator.

kayba-ai/agentic-context-engine · 64 tokens

playwright-screen-recording

Record browser test videos with Playwright for PR review and bug fix verification.

liaohch3/claude-tap · 20 tokens

kayba-stage-1-api-analysis

Fetch pre-computed insights from the Kayba API and build a structured summary. Does NOT upload traces or trigger generation — analysis is assumed to already exist. Trigger when the user says "run stage 1", "get insights", "fetch skills", "kayba analyze", or when invoked by the kayba-pipeline orchestrator. Requires the…

kayba-ai/agentic-context-engine · 93 tokens