docs-mcp-server: Skill for Claude Code

.agents/skills/apple-docc-tenant/SKILL.md

apple-docc-tenant is a skill for Claude Code from pankaj28843/docs-mcp-server. It costs 149 tokens per session (3,064 once invoked), scanned C, original, MIT.

A workflow for maintaining a searchable copy of Apple’s developer documentation. Apple DocC is the system Apple uses to publish its programming documentation.

In plain words
What is it for?
Use it to refresh, repair, export, and verify a documentation search tenant built from Apple’s DocC data and rendered pages.
Why use it?
Apple’s documentation website relies heavily on JavaScript, so its useful content is difficult to crawl and index directly.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is pankaj28843/docs-mcp-server's own configuration. It tells Claude Code how to work on docs-mcp-server 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 docs-mcp-server configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run python scripts/apple_rendered_link_bfs.py --help.

Reuse

Borrowing it

Nothing to install: this file belongs to pankaj28843/docs-mcp-server. 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/pankaj28843/docs-mcp-server/main/.agents/skills/apple-docc-tenant/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/pankaj28843/docs-mcp-server

Made for: Claude Code.

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 apple-docc-tenant

README.md
[![agentmods](https://agentmods.dev/badge/skills/pankaj28843/docs-mcp-server/apple-docc-tenant/github.svg)](https://agentmods.dev/skills/pankaj28843/docs-mcp-server/apple-docc-tenant)
Your own site
<a href="https://agentmods.dev/skills/pankaj28843/docs-mcp-server/apple-docc-tenant"><img src="https://agentmods.dev/badge/skills/pankaj28843/docs-mcp-server/apple-docc-tenant/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 apple-docc-tenant

Your own site · 80×15
<a href="https://agentmods.dev/skills/pankaj28843/docs-mcp-server/apple-docc-tenant"><img src="https://agentmods.dev/badge/skills/pankaj28843/docs-mcp-server/apple-docc-tenant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 149 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,064 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00149 $0.03064
Opus 5 $0.00075 $0.01532
Sonnet 5 $0.00030 $0.00613
Haiku 4.5 $0.00015 $0.00306

Measured 10d ago against content hash bd2d116ca28f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

apple-docc-tenant scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

sleep 15 && curl -sf http://127.0.0.1:42042/health | python3 -c \

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

sleep 15 && curl -sf http://127.0.0.1:42042/health | python3 -c \
.agents/skills/apple-docc-tenant/SKILL.md · 312 lines

How it starts

The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Apple DocC Tenant Workflow

Apple Developer Documentation is not a normal online tenant. The public page is a JavaScript DocC shell, useful content is DocC JSON under /tutorials/data/documentation/, and some public docs are only reliably found by visiting hydrated documentation pages and reading their anchors.

All-docs rule: if an Apple documentation URL exists under https://developer.apple.com/documentation/, it must be discovered, rendered, indexed, and fetchable by docsearch. Do not use --max-docs caps for final Apple refreshes. Use the rendered-link BFS plus the DocC JSON graph, then render as a filesystem tenant.

Preconditions

  • Work from the repo root.
  • uv sync --extra dev has been run.
  • cdp is on PATH for rendered browser crawling and diagnostics.
  • deployment.json is backed up before edits because it is git-ignored.
mkdir -p tmp/backups && cp deployment.json "tmp/backups/deployment.json.$(date +%Y%m%d-%H%M%S)"

Step 1: Verify cdp locally before browser work

cdp --help is the source of truth. Do not assume flags and do not switch to Playwright, Selenium, or a headless fallback.

command -v cdp
cdp --help
cdp open --help
cdp eval --help
cdp wait eval --help
cdp workflow --help
cdp workflow page-load --help
cdp workflow debug-bundle --help
cdp workflow rendered-extract --help
cdp workflow network-failures --help
cdp doctor --check daemon --json
cdp doctor --check browser-health --json
cdp daemon health --json
uv run python scripts/apple_rendered_link_bfs.py --help
uv run python scripts/apple_rendered_link_bfs.py --preflight-only

If cdp reports a human-required browser approval or unhealthy daemon, stop and ask the human to approve/repair it.

Step 2: Capture Apple DocC evidence when stuck

Save transient artifacts under tmp/cdp/apple-developer/:

mkdir -p tmp/cdp/apple-developer
cdp workflow page-load "https://developer.apple.com/documentation/" \
  --out tmp/cdp/apple-developer/page-load.json \
  --wait 10s \
  --json
cdp workflow debug-bundle \
  --url "https://developer.apple.com/documentation/" \
  --out-dir tmp/cdp/apple-developer/debug-bundle \
  --screenshot-view \
  --json
cdp workflow network-failures \
  --url-contains "developer.apple.com" \
  --wait 5s \
  --limit 0 \
  --json > tmp/cdp/apple-developer/network-failures.json

Read the full file on GitHub · 312 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. 10d ago First seen · 312 lines · 149 tokens per session scan C bd2d116ca28f

Subscribe to this mod's changes

apple-docc-tenant is a skill published in the GitHub repository pankaj28843/docs-mcp-server (2 stars, last pushed 12d ago), licensed MIT. It adds 149 tokens to every session and 3,064 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

book-to-skill

Book-to-skill takes technical books, documentation, or other long-form sources and converts them into a skill made of a core definition plus per-chapter files, a glossary, and cheatsheets, so an agent can load only the relevant section instead of the whole document. It supports PDF, EPUB, DOCX, HTML, and several other…

best-of-ai/best-of-ai · 75 tokens

write-ops-runbook

Use when documenting a repeatable operational procedure that on-call engineers or operators must execute under pressure.

jeffreytse/grimoire-core · 24 tokens

convert-documents-to-markdown

Convert an attached Word document, presentation, spreadsheet, OpenDocument file, RTF, EPUB, CSV, or text-based PDF into local Markdown. Use when a message supplies a local attachment path that must be read without uploading it to an external parser.

nanocoai/nanoclaw · 57 tokens

sn-ppt-entry

Entry point for PPT generation. Asks the user to choose a mode (fast, standard, or creative), then collects role / audience / scene / pagecount as needed. For standard mode, also asks how images should be sourced (AI generation, web search, or none), whether charts should use AI-generated infographics or ECharts, and…

OpenSenseNova/SenseNova-Skills · 204 tokens

pdf-analysis

A PDF analysis method for reading both normal PDFs with selectable text and scanned PDFs made from page images.

OpenSenseNova/SenseNova-Skills · 48 tokens

ppt-analysis

A parser for PowerPoint presentations in .pptx or older .ppt format that extracts their contents and flags slides needing image-based inspection.

OpenSenseNova/SenseNova-Skills · 51 tokens