q-compact

q-compact is a command for Claude Code from contactTAM/q-command-system. It costs 10 tokens per session (399 once invoked), scanned A, original, MIT.

A command that saves a detailed session checkpoint before asking the coding assistant to reduce its conversation context.

In plain words
What is it for?
Use it when the conversation is getting full and you need to continue working with more available context.
Why use it?
It preserves important work details before context is shortened, so the session can continue with less risk of losing decisions or progress.

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/contacttam/q-command-system/q-compact
Clone the repo
git clone --depth 1 https://github.com/contactTAM/q-command-system

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 q-compact

README.md
[![agentmods](https://agentmods.dev/badge/commands/contacttam/q-command-system/q-compact.svg)](https://agentmods.dev/commands/contacttam/q-command-system/q-compact)
Your own site
<a href="https://agentmods.dev/commands/contacttam/q-command-system/q-compact"><img src="https://agentmods.dev/badge/commands/contacttam/q-command-system/q-compact.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 399 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 $0.00010 $0.00399
Opus 5 $0.00005 $0.00199
Sonnet 5 $0.00002 $0.00080
Haiku 4.5 $0.00001 $0.00040

Measured 3d ago against content hash 6f4472ee3543, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

q-compact 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 3d 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.

templates/.claude/commands/q-compact.md · 66 lines

What it actually says

Safe Compact

Purpose: Free up context space by saving a checkpoint first, then compacting. Protects your work while giving more room to continue.

Why Use /q-compact Instead of /compact Directly

  • /compact alone summarizes and loses detail
  • /q-compact saves a checkpoint FIRST, then compacts
  • Your detailed work history is preserved in the checkpoint file
  • You get more context space AND keep your work safe

Step 1: Create Checkpoint

Execute /q-checkpoint to save current progress.

Wait for confirmation that checkpoint was saved.

Step 2: Run Compact

Tell the user:

Checkpoint saved. Now run this command:

/compact Preserve: key decisions, files changed, current task status. This is a /q-compact operation - checkpoint already saved.

Or if you can execute /compact directly, do so with that prompt.

Step 3: Report Results

/q-compact complete!

Checkpoint saved: .q-system/checkpoints/[filename]
Context compacted: More space available

Your detailed work is preserved in the checkpoint.
/q-end will merge checkpoint + remaining work into complete session notes.

Tip: Run /context to see your new context usage.

When to use:

  • Context usage above 70%
  • After /context shows high usage
  • Before starting a large new task
  • When Claude's responses are getting slower

Example workflow:

[Working for 90 minutes, context getting full]
User: /context              → Shows 75% usage
User: /q-compact            → Saves checkpoint, then compacts
                            → Now at ~30% usage
[Continue working with fresh context]
User: /q-end                → Merges checkpoint + new work
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. 3d ago First seen · 66 lines · 10 tokens per session scan A 6f4472ee3543

Subscribe to this mod's changes

q-compact is a command published in the GitHub repository contactTAM/q-command-system (5 stars, last pushed 8mo ago), licensed MIT. It adds 10 tokens to every session and 399 once invoked, about $0.0001 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 2026-08-31.