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.
npx agentmods add commands/contacttam/q-command-system/q-paregit clone --depth 1 https://github.com/contactTAM/q-command-systemWrote 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.
[](https://agentmods.dev/commands/contacttam/q-command-system/q-pare)<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>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 5.1 | $0.00010 | $0.00573 |
| Opus 5 | $0.00005 | $0.00287 |
| Sonnet 5 | $0.00002 | $0.00115 |
| Haiku 4.5 | $0.00001 | $0.00057 |
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.
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
- 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.
- 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.
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.
- 5d ago First seen · 97 lines · 10 tokens per session scan A fd3f7e942695
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.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
session-end
I'll summarize this coding session and update the memory system with our accomplishments.
memory-store
Store an insight, decision, or pattern to memory.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.