Sample Agent Skills for Builders is a collection of reusable skills that extend AI coding agents with AWS, CDK, security, testing, and engineering workflows. Developers can install the skills for practical AWS development tasks or use the repository as a model for creating their own agent skills. The catalogue entries are skills and instructions from this collection.
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 skills/aws-samples/sample-agent-skills-for-builders/gitlab-docs-publishingnpx skills add aws-samples/sample-agent-skills-for-builders --skill gitlab-docs-publishinggit clone --depth 1 https://github.com/aws-samples/sample-agent-skills-for-buildersWrote 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.
[](https://agentmods.dev/skills/aws-samples/sample-agent-skills-for-builders/gitlab-docs-publishing)<a href="https://agentmods.dev/skills/aws-samples/sample-agent-skills-for-builders/gitlab-docs-publishing"><img src="https://agentmods.dev/badge/skills/aws-samples/sample-agent-skills-for-builders/gitlab-docs-publishing.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00097 | $0.01377 |
| Opus 5 | $0.00048 | $0.00688 |
| Sonnet 5 | $0.00019 | $0.00275 |
| Haiku 4.5 | $0.00010 | $0.00138 |
Grade A, and why
gitlab-docs-publishing 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 5d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitLab Docs Publishing
Publish styled HTML design docs on GitLab Pages and let reviewers file in-context feedback by selecting any text and clicking a floating 💬 bubble — which opens a pre-filled GitLab Issue in a new tab. Zero external services, zero in-page API calls.
Standalone HTML design docs are great for reading but miss two things GitLab
does not provide out of the box: a public URL (GitLab renders .html blobs
as source code, not as a page) and an in-context comment thread tied to the
exact piece of prose a reviewer wants to discuss. This skill bolts both on
using only free GitLab features:
- GitLab Pages auto-publishes HTML on every merge to main.
- Selection-driven 💬 bubble — a small JS widget watches text selection.
On click, it navigates the browser to GitLab's "New issue" page with title
- description + label prefilled. GitLab authenticates the user with their existing session cookie.
When to Apply
- Publishing a technical design doc (HTML or Markdown) for team review.
- Teammates complain they have to
git cloneto see the styled HTML version. - Meeting feedback gets lost because there's no place to write it against specific sentences.
- An HTML visual doc has been generated from source Markdown and now needs a distribution channel with feedback affordances.
Not for:
- Documents that belong in GitLab Wiki (Wiki renders Markdown natively and has built-in comments).
- Single-reviewer review — use MR line comments instead.
- External/public audiences who do not have GitLab accounts.
How It Works
docs/<v>/foo.html
│
│ inject-comments.py:
│ 1. Strip any pre-existing in-page widgets
│ 2. Add ids to headings/figures/tables
│ 3. Inject <link>+<script> for the selection-bubble widget
│ 4. Copy comment-widget.{js,css} into <assets-dir>
↓
public/<v>/index.html ──▶ GitLab Pages CI publishes public/
↓
Reviewer opens published URL
Selects any text → 💬 bubble appears
Clicks → new tab on GitLab issues/new
with title + description + label prefilled
GitLab uses existing session cookie
Reviewer types → submits → labelled Issue created
What ships with it
8 files 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.
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.
- 5d ago First seen · 138 lines · 97 tokens per session scan A f9a5855c473b
gitlab-docs-publishing is a skill published in the GitHub repository aws-samples/sample-agent-skills-for-builders (47 stars, last pushed 8d ago), licensed Apache-2.0. It adds 97 tokens to every session and 1,377 once invoked, about $0.0005 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 skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
Two-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI. Use when user says "同步 overleaf", "overleaf sync", "推送到 overleaf", "connect overleaf", "Overleaf 桥接", "pull overleaf", "push overleaf", or wants to…
pdf-verification-cli
Verify PDF page count and content using command-line tools when Python libraries unavailable.