q-pare

q-pare is a command for Claude Code from contactTAM/q-command-system. It costs 10 tokens per session (573 once invoked), scanned A, original, MIT.

A command that shortens the always-loaded CLAUDE.md project instructions by moving detailed reference material into an OFFLOAD.md file.

In plain words
What is it for?
Use it to review CLAUDE.md, decide what belongs in the main instructions, and create or update OFFLOAD.md with detailed commands, schemas, deployment notes, and other reference material.
Why use it?
It keeps routine agent sessions focused on essential project information, while preserving less frequently needed documentation for later reference.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

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-pare
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-pare

README.md
[![agentmods](https://agentmods.dev/badge/commands/contacttam/q-command-system/q-pare.svg)](https://agentmods.dev/commands/contacttam/q-command-system/q-pare)
Your own site
<a href="https://agentmods.dev/commands/contacttam/q-command-system/q-pare"><img src="https://agentmods.dev/badge/commands/contacttam/q-command-system/q-pare.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 573 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 5.1 $0.00010 $0.00573
Opus 5 $0.00005 $0.00287
Sonnet 5 $0.00002 $0.00115
Haiku 4.5 $0.00001 $0.00057

Measured 5d ago against content hash fd3f7e942695, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

q-pare 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.

templates/.claude/commands/q-pare.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pare CLAUDE.md

Purpose: Optimize CLAUDE.md by moving less-critical reference material to OFFLOAD.md. Since CLAUDE.md is always loaded into context, keeping it lean improves performance.

Step 1: Analyze CLAUDE.md

Read CLAUDE.md and identify content by category:

KEEP in CLAUDE.md (essential for every session):

  • Project overview (1-2 paragraphs max)
  • Tech stack (brief list)
  • Core architecture (overview only)
  • Key workflows and commands
  • Critical policies (git push policy, etc.)
  • Team member names
  • Important constraints

MOVE to OFFLOAD.md (useful but not needed every time):

  • Detailed command examples
  • Complete file structure listings
  • Full environment variable documentation
  • Detailed deployment procedures
  • Extended history or background
  • Reference links
  • Detailed code examples
  • Complete schema documentation
  • Testing procedures (detailed)

Step 2: Create/Update OFFLOAD.md

Create or update OFFLOAD.md in project root:

# OFFLOAD.md - Extended Documentation

This file contains detailed reference material extracted from CLAUDE.md to optimize context loading. Consult this file when you need detailed specifications.

---

## [Section Name]

[Moved content with original formatting preserved]

## [Section Name]

[Moved content...]

Step 3: Update CLAUDE.md

  1. Add pointer section near the top (after project overview):
## Extended Documentation

For detailed reference material (full commands, environment setup, deployment procedures, etc.), see `OFFLOAD.md`. This file is kept lean for optimal context loading.
  1. Replace verbose sections with summaries:
    • Keep essential info
    • Add "See OFFLOAD.md for details" where appropriate
    • Maintain structure but reduce verbosity

Step 4: Verify and Report

CLAUDE.md Optimized

Moved to OFFLOAD.md:
- [Section 1]
- [Section 2]
- [Section 3]

CLAUDE.md changes:
- Before: ~[N] lines
- After: ~[M] lines ([X]% reduction)
- Added pointer to OFFLOAD.md
- Maintained all essential guidance

Both files ready. CLAUDE.md is now optimized for context loading.

Read the full file on GitHub · 97 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 · 97 lines · 10 tokens per session scan A fd3f7e942695

Subscribe to this mod's changes

q-pare 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 573 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.