skills CLAUDE.md

Repository instructions for developing and maintaining browser-automation skills. They describe the project layout, how skills are installed, and how Playwright commands must identify the browser tab they operate on.

In plain words
What is it for?
Use them when editing this skills repository, building page-migration skills, or automating a browser with Playwright inside Slicc.
Why use it?
They give agents the project conventions needed to make compatible changes and avoid sending browser actions to the wrong tab. They also document where migration skills and supporting scripts belong.

Instructions file

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 instructions/aemcoder/skills/claude-md
Clone the repo
git clone --depth 1 https://github.com/aemcoder/skills
Per session 1,546 This file is loaded in full into every session.
When invoked 1,546 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.01546 $0.01546
Opus 5 $0.00773 $0.00773
Sonnet 5 $0.00309 $0.00309
Haiku 4.5 $0.00155 $0.00155

Measured 2d ago against content hash a1881a54c3aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skills CLAUDE.md scanned grade A with 1 finding 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 2d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

in the bridge) and `child_process`.
CLAUDE.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Instructions for developing and maintaining skills in this repository.

Repository Structure

skills/migration/
  migrate-page/SKILL.md      Cone-only: orchestrates full page migration
  migrate-block/SKILL.md     Scoop: migrates a single block with visual verification
  migrate-header/SKILL.md    Scoop: migrates header/nav with EDS header block pattern
  dismiss-overlays/SKILL.md  Reference: overlay dismissal patterns
docs/specs/                  Design docs and implementation plans

Skills live under a top-level skills/ directory (Anthropic skills convention), with migration/ as a category subdir. Install commands target --path skills/migration. Slicc's upskill flattens the inner skill folders into /workspace/skills/<name>/ at runtime — so internal references like /workspace/skills/migrate-page/scripts/... are unaffected by the source layout.

Slicc Browser Automation Conventions

Skills run inside Slicc and use playwright-cli for browser automation.

Stateless Tab Targeting (since slicc PR #188)

Every playwright-cli command that operates on a tab requires explicit --tab <targetId>. There is no implicit "current tab".

Capture targetId from output:

# tab-new returns a targetId
playwright-cli tab-new https://example.com
# Output: "Created tab <targetId> at https://example.com"
# Capture <targetId> as {sourceTabId}

# open also returns a targetId (and does NOT broadcast/steal focus)
open /shared/my-site/drafts/hero-preview.html
# Output: "... (targetId: <targetId>)"
# Capture <targetId> as {previewTabId}

Use --tab on every command:

playwright-cli eval --tab={sourceTabId} "document.title"
playwright-cli screenshot --tab={previewTabId} --max-width=1440 --filename=out.png
playwright-cli snapshot --tab={previewTabId}
playwright-cli goto --tab={previewTabId} {url}
playwright-cli tab-close --tab={sourceTabId}

Commands without --tab: tab-list (lists all tabs), tab-new (creates a tab).

Read the full file on GitHub · 141 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. 2d ago First seen · 141 lines · 1,546 tokens per session scan A a1881a54c3aa

Subscribe to this mod's changes

skills CLAUDE.md is an instructions file published in the GitHub repository aemcoder/skills (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 1,546 tokens to every session, about $0.0077 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.