grackle: Skill for Claude Code

.claude/skills/demo-record/SKILL.md

demo-record is a skill for Claude Code from nick-pape/grackle. It costs 33 tokens per session (1,145 once invoked), scanned A, original, MIT.

A launcher for a self-recording Grackle demo, where an AI agent controls a browser with Playwright, narrates actions, and records the screen. It prepares Docker containers and a fresh Grackle database first.

In plain words
What is it for?
Building the demo and development images, clearing previous state, creating a project and task, and starting the recording agent.
Why use it?
It avoids stale projects and tasks appearing during a recording and sets up the supporting services in a repeatable way.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths; mentions Claude Code.

This is nick-pape/grackle's own configuration. It tells Claude Code how to work on grackle 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 grackle configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node packages/server/dist/index.js --port=7434 --web-port=3000 &.

Reuse

Borrowing it

Nothing to install: this file belongs to nick-pape/grackle. 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/nick-pape/grackle/main/.claude/skills/demo-record/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/nick-pape/grackle

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 demo-record

README.md
[![agentmods](https://agentmods.dev/badge/skills/nick-pape/grackle/demo-record/github.svg)](https://agentmods.dev/skills/nick-pape/grackle/demo-record)
Your own site
<a href="https://agentmods.dev/skills/nick-pape/grackle/demo-record"><img src="https://agentmods.dev/badge/skills/nick-pape/grackle/demo-record/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 demo-record

Your own site · 80×15
<a href="https://agentmods.dev/skills/nick-pape/grackle/demo-record"><img src="https://agentmods.dev/badge/skills/nick-pape/grackle/demo-record.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,145 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 $0.00033 $0.01145
Opus 5 $0.00016 $0.00573
Sonnet 5 $0.00007 $0.00229
Haiku 4.5 $0.00003 $0.00114

Measured 9d ago against content hash 36ce6c40783f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

demo-record 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 9d 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.

.claude/skills/demo-record/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Launch Grackle Demo Recording

This skill sets up and launches the self-recording Grackle demo where a Claude Code agent inside Docker controls a browser with Playwright MCP, narrates with PocketTTS MCP, and records its own screen with ffmpeg.

Prerequisites

  • Grackle server must be running (node packages/server/dist/index.js or grackle serve)
  • Docker Desktop must be running
  • ANTHROPIC_API_KEY must be set (or ~/.claude/.credentials.json mounted)

Steps

1. Build all packages

rush build

2. Build Docker images

# Demo recorder image (Playwright + Xvfb + PulseAudio + ffmpeg + PocketTTS)
# No --secret needed: uses PocketTTS built-in voices (no HF_TOKEN required)
docker build -f docker/Dockerfile.demo-recorder -t grackle-demo-recorder .

# Dev environment image (standard PowerLine)
docker build -f docker/Dockerfile.powerline -t grackle-powerline .

3. Nuke database and restart server

The demo must start with a completely clean database — no leftover projects, tasks, or findings from previous runs. Stale data causes the demo agent to see pre-existing tasks instead of creating them fresh on camera.

# Kill the grackle server (it holds the DB lock)
# Windows (Git Bash): find PID with `wmic process where "name='node.exe'" get processid,commandline | grep server`
# then: taskkill /PID <SERVER_PID> /F
# Linux/Mac: kill $(pgrep -f "node.*server/dist/index.js")

# Delete the database
rm -f ~/.grackle/grackle.db ~/.grackle/grackle.db-wal ~/.grackle/grackle.db-shm

# Restart the server
node packages/server/dist/index.js --port=7434 --web-port=3000 &

Also stop and remove any existing containers:

docker stop grackle-demo-recorder grackle-dev grackle-dev2 2>/dev/null
docker rm grackle-demo-recorder grackle-dev grackle-dev2 2>/dev/null

4. Add and provision environments

Since the DB was nuked, environments must be re-added and provisioned:

# Demo recorder with the full AV stack
grackle env add demo-recorder --docker --image grackle-demo-recorder --runtime claude-code

# Dev environments with repo clone (the demo agent creates tasks on these live)
grackle env add dev --docker --image grackle-powerline --runtime claude-code --repo nick-pape/grackle
grackle env add dev2 --docker --image grackle-powerline --runtime claude-code --repo nick-pape/grackle

# Provision all three
grackle env provision demo-recorder
grackle env provision dev
grackle env provision dev2

Read the full file on GitHub · 134 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. 9d ago First seen · 134 lines · 33 tokens per session scan A 36ce6c40783f

Subscribe to this mod's changes

demo-record is a skill published in the GitHub repository nick-pape/grackle (21 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 1,145 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.