pack

A command that collects a repository's files into one file for use as background information in an AI chat or issue.

In plain words
What is it for?
Pack a local or remote repository, choose which files to include, select XML, Markdown, or JSON output, and optionally add Git changes and logs.
Why use it?
It avoids manually gathering source files and project context when asking an AI or teammate for help.

Command

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/sergei-aronsen/claude-code-toolkit/pack
Clone the repo
git clone --depth 1 https://github.com/sergei-aronsen/claude-code-toolkit
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 1,216 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 $0.00000 $0.01216
Opus 5 $0.00000 $0.00608
Sonnet 5 $0.00000 $0.00243
Haiku 4.5 $0.00000 $0.00122

Measured 2d ago against content hash 12ca30a90814, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

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.

commands/pack.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/pack — Repository Pack for AI Context

Purpose

Pack the current repository (or a remote one) into a single AI-friendly file via Repomix. The output lands in .claude/scratchpad/ and is ready to attach to any LLM — ChatGPT, Claude web, Gemini, a teammate, an issue thread.

This is the manual counterpart to /council's automatic pack augmentation. Use it when you want a snapshot outside the Council flow.


Usage

/pack                                 # local repo, defaults (XML, compressed)
/pack --remote yamadashy/repomix      # remote repo by shorthand
/pack --remote https://github.com/x/y # full URL
/pack --include "src/**,*.md"         # filter
/pack --format markdown               # md instead of xml
/pack --format json                   # json
/pack --to clipboard                  # copy to system clipboard (pbcopy/xclip)
/pack --no-compress                   # skip tree-sitter signature extraction
/pack --include-diffs --include-logs  # add git context

Examples:

  • /pack — pack this repo, write .claude/scratchpad/pack-<timestamp>.xml
  • /pack --remote nestjs/nest --include "packages/core/**" — pack a subset of an upstream repo
  • /pack --to clipboard --format md — quick markdown handoff for ChatGPT
  • /pack --include-diffs --include-logs — pack with full git history (last 50 commits)

When to Use

Situation Use /pack
Architectural review across 50+ files yes
Handoff to another LLM (ChatGPT, web Claude) yes
Attach codebase context to an issue / PR comment yes
Snapshot for a teammate working in a different stack yes
Look at the shape of an upstream library yes (--remote)
Find a single function no — use /find-function or Grep
Read one file no — use Read
Open-ended exploration of 2-3 files no — use Explore agent
Pre-Council context no — Council does this automatically via --pack

Read the full file on GitHub · 135 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 · 135 lines · 0 tokens per session scan A 12ca30a90814

Subscribe to this mod's changes

pack is a command published in the GitHub repository sergei-aronsen/claude-code-toolkit (5 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,216 tokens. 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 2026-08-31.