use-pack

use-pack is a command for Claude Code from opensesh/karimo-overview. It costs 7 tokens per session (551 once invoked), scanned A, original, Apache-2.0.

A command for loading a named set of specialist guidance into the coding session, such as accessibility, performance, security, database, or user-experience work.

In plain words
What is it for?
Use it before tasks like checking WCAG accessibility, measuring website speed, reviewing security, analysing PostgreSQL queries, or planning usability research.
Why use it?
It avoids repeating specialist instructions and rules each time you need that kind of help.

Command for Claude Code

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/opensesh/karimo-overview/use-pack
Clone the repo
git clone --depth 1 https://github.com/opensesh/karimo-overview

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 use-pack

README.md
[![agentmods](https://agentmods.dev/badge/commands/opensesh/karimo-overview/use-pack.svg)](https://agentmods.dev/commands/opensesh/karimo-overview/use-pack)
Your own site
<a href="https://agentmods.dev/commands/opensesh/karimo-overview/use-pack"><img src="https://agentmods.dev/badge/commands/opensesh/karimo-overview/use-pack.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 551 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00007 $0.00551
Opus 5 $0.00003 $0.00275
Sonnet 5 $0.00001 $0.00110
Haiku 4.5 $0.00001 $0.00055

Measured 5d ago against content hash 218a8c60c592, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

use-pack 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 5d 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/commands/use-pack.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/use-pack - Agency Pack Activation

Activate a third-party agent pack for specialized capabilities.

Usage

/use-pack <pack-name>

Available Packs

Pack Description
a11y WCAG 2.2 AA compliance, screen reader testing, React Aria validation
perf Core Web Vitals, Lighthouse automation, bundle analysis
security Threat modeling, secure code review, OWASP Top 10
database Supabase/PostgreSQL query analysis, index optimization
ux User research frameworks, usability testing, persona development

Instructions

When a user runs /use-pack <pack-name>:

  1. Validate the pack name from the list above
  2. Read the agent file from .claude/agency-packs/<pack>/<agent>.md
  3. Load the agent's full context including BOS-specific rules
  4. Confirm activation with a brief summary of capabilities
  5. Apply the agent's expertise to subsequent tasks in this session

Pack Locations

.claude/agency-packs/
├── a11y/accessibility-auditor.md
├── perf/performance-benchmarker.md
├── security/security-engineer.md
├── database/database-optimizer.md
└── ux/ux-researcher.md

Activation Response Template

When a pack is activated, respond with:

**{Pack Name} Activated**

I'll now apply {agent name} expertise to your tasks:
- {Capability 1}
- {Capability 2}
- {Capability 3}

BOS context loaded: {relevant BOS integrations}

What would you like me to help with?

Example

User: /use-pack a11y

Response:

**Accessibility Pack Activated**

I'll now apply accessibility auditor expertise to your tasks:
- WCAG 2.2 AA compliance auditing
- Screen reader testing (VoiceOver, NVDA)
- React Aria component validation
- Keyboard navigation verification

BOS context loaded: React Aria Components, UUI semantic tokens, devProps standards

What would you like me to audit for accessibility?

Error Handling

If pack name is invalid:

Unknown pack: {name}

Available packs:
- a11y: Accessibility auditing
- perf: Performance benchmarking
- security: Security engineering
- database: Database optimization
- ux: UX research

Usage: /use-pack <pack-name>

Read the full file on GitHub · 99 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. 5d ago First seen · 99 lines · 7 tokens per session scan A 218a8c60c592

Subscribe to this mod's changes

use-pack is a command published in the GitHub repository opensesh/karimo-overview (11 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 7 tokens to every session and 551 once invoked, about $0.0000 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.