A one-time setup command for configuring Claude or Cursor hooks, which are automated actions run by those coding tools.

Use it to choose project-wide or computer-wide installation, check required example files, create work logs, copy configuration files, and run hook tests.

It prepares a project or computer for these hooks and helps keep setup files and work logs in the expected locations.

setup — Command by laaibaQasim

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 commands/laaibaqasim/productivity-kit/setup

Clone the repo

git clone --depth 1 https://github.com/laaibaQasim/productivity-kit

Made for: Cursor.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,062 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.02062
Opus 5	$0.00000	$0.01031
Sonnet 5	$0.00000	$0.00412
Haiku 4.5	$0.00000	$0.00206

Measured 2d ago against content hash b92df4b74d79, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

setup scanned grade B 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

### 3. Write `~/.claude/settings.json`

.cursor/commands/setup.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Setup this project.

description: >- Initialize ai-dump: create work-logs, copy example configs, update .git/info/exclude, run hook tests. Supports project-level and system-level (~/.claude / ~/.cursor) installation.

Setup

One-time local setup for Claude/Cursor hooks in this repo.

Before doing anything else, ask the user:

"Do you want to install hooks at the project level (everything stays in this repo — only affects this project) or at the system level (hooks live in ~/.claude/ and ~/.cursor/ and apply to every project on this machine)?"

Wait for their answer, then follow the matching option below.

Option A — Project-level setup

Set up this repository for local Claude/Cursor hook usage.

Follow this exact flow:

First, inspect the repo and confirm these paths:
- .claude/config.json.example
- .cursor/config.json.example
- .claude/hooks/__tests__
- .cursor/hooks/__tests__ (optional)
- .git/ (optional, only if this is a git repo)
Do the setup work:
- Create work-logs/ in the repository root if it does not already exist.
- If .claude/config.json does not exist and .claude/config.json.example exists, copy the example file to .claude/config.json.
- If .cursor/config.json does not exist and .cursor/config.json.example exists, copy the example file to .cursor/config.json.
- Never overwrite an existing config.json without asking.
- If this repo has a .git/ directory:
  - Ensure .git/info/ exists.
  - Ensure .git/info/exclude contains these exact lines, adding only missing ones:
    - work-logs/
    - .claude/config.json
    - .cursor/config.json
Run tests:
- If .claude/hooks/__tests__ exists, run: node --test .claude/hooks/__tests__
- If .cursor/hooks/__tests__ exists, also run: node --test .cursor/hooks/__tests__
- If Node is missing, stop and explain that Node is required.
When finished, give a concise summary that includes:
- Whether config files were created
- Whether work-logs/ was created
- Whether .git/info/exclude was updated
- Whether tests passed

Read the full file on GitHub · 222 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.

2d ago First seen · 222 lines · 0 tokens per session scan B b92df4b74d79

Subscribe to this mod's changes

setup is a command published in the GitHub repository laaibaQasim/productivity-kit (4 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,062 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

claude-hooks claude-notification cursor-hooks github logging logs-analysis

setup

Getting it into your agent

What it costs to keep this loaded

Grade B, and why

Reads agent configuration directoriesmediumAgent snooping

How it starts

Setup this project.

description: >- Initialize ai-dump: create work-logs, copy example configs, update .git/info/exclude, run hook tests. Supports project-level and system-level (~/.claude / ~/.cursor) installation.

Setup

Option A — Project-level setup

What this file has done since we first saw it

Other commands, from other repositories

create-hook

VibeGuard: Stats

oss

setup-oss

nyann:diff-profile

plan