lynx-website: Skill for Claude Code

.agents/skills/generate-cdp-spec/SKILL.md

generate-cdp-spec is a skill for Claude Code, Codex from lynx-family/lynx-website. It costs 60 tokens per session (1,223 once invoked), scanned A, original, Apache-2.0.

A documentation generator for the Lynx DevTool CDP API, a browser-debugging protocol interface. It builds English reference pages from an authoritative generated manifest and then requires a Chinese translation.

In plain words
What is it for?
Use it to regenerate or check CDP API documentation, including custom method descriptions, after validating the required Lynx source files.
Why use it?
It keeps the published protocol reference tied to its source metadata and separates generated content from the source repository that defines the protocol.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is lynx-family/lynx-website's own configuration. It tells Claude Code and Codex how to work on lynx-website 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 lynx-website configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lynx-family/lynx-website. 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/lynx-family/lynx-website/main/.agents/skills/generate-cdp-spec/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lynx-family/lynx-website

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 generate-cdp-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/lynx-family/lynx-website/generate-cdp-spec/github.svg)](https://agentmods.dev/skills/lynx-family/lynx-website/generate-cdp-spec)
Your own site
<a href="https://agentmods.dev/skills/lynx-family/lynx-website/generate-cdp-spec"><img src="https://agentmods.dev/badge/skills/lynx-family/lynx-website/generate-cdp-spec/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 generate-cdp-spec

Your own site · 80×15
<a href="https://agentmods.dev/skills/lynx-family/lynx-website/generate-cdp-spec"><img src="https://agentmods.dev/badge/skills/lynx-family/lynx-website/generate-cdp-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,223 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.
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 $0.00060 $0.01223
Opus 5.5 $0.00024 $0.00489
Sonnet 5.5 $0.00012 $0.00245
Haiku 4.5 $0.00006 $0.00122

Measured 1mo ago against content hash 883c0cfdb306, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

generate-cdp-spec 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 1mo 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.

.agents/skills/generate-cdp-spec/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate the CDP Spec

Use the existing website generator. The Lynx source repository owns protocol metadata and custom method documentation; this repository owns the generated MDX and its presentation.

Locate the inputs

Run commands from the website repository root. Find the open-source Lynx checkout from the user's context or nearby checkouts, and verify these inputs:

  • devtool/lynx_devtool/protocol/cdp_manifest.generated.yaml
  • devtool/lynx_devtool/protocol/custom_cdp_docs/

Use the requested checkout or revision. If the inputs cannot be found, ask for the checkout path. Treat the generated manifest as authoritative for the protocol inventory and metadata, and the accompanying custom docs as the source for method details. Do not override them with assumptions from existing website pages, implementation code, or upstream CDP documentation.

If input validation fails or any suspected defect is found in the inputs, generator, or generated content, stop and prompt the user with the affected file or method, the evidence, and the decision needed. Wait for the user's direction before proceeding. Do not edit or regenerate the input manifest, patch custom docs or the generator, or work around the defect in the output. Ordinary missing or stale generated pages are expected regeneration work; they do not by themselves indicate an input or generator defect.

The default output base is docs/en/api/cdp/api-ref. Respect an explicitly requested alternative. --output-path must have no file extension; it produces <base>.mdx, <base>/<domain>.mdx, and <base>/_meta.json.

For input schemas, rendering details, or validation failures, read the generator guide.

Generate or check

Use Python 3 with PyYAML. Reuse a suitable environment; if needed, create a virtual environment in the website checkout and install the dependency:

python3 -m venv .venv
.venv/bin/python -m pip install PyYAML

Set LYNX_ROOT to the verified checkout path. With that environment, regenerate the English reference using:

Read the full file on GitHub · 121 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. 1mo ago First seen · 121 lines · 60 tokens per session scan A 883c0cfdb306

Subscribe to this mod's changes

generate-cdp-spec is a skill published in the GitHub repository lynx-family/lynx-website (131 stars, last pushed yesterday), licensed Apache-2.0. It adds 60 tokens to every session and 1,223 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-12.

Related

generate-cdp-spec compared with skills from other repositories

generate-cdp-spec next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
generate-cdp-speclynx-family/lynx-websiteSkill131yesterdayApache-2.0A60Claude Code, Codex
computer-useThinkInAIXYZ/deepchatSkill6.4kyesterdayApache-2.0A40Claude Code, Codex
browser-cdpuu201/character-arcSkill600yesterdayMITA94Claude Code, Codex
youtube-watcherMerkyorLynn/LynnSkill676d agoApache-2.0A34Claude Code, Codex
computer-usePlocr/Reasonix-computer-useSkill433mo agoMITA23Claude Code
web-navigatorPlocr/Reasonix-computer-useSkill433mo agoMITA30Claude Code
2-captchajnotsknab/mux-swarmSkill9yesterdayGPL-3.0A34Claude Code, Codex