q-begin

q-begin is a command for Claude Code from contactTAM/q-command-system. It costs 5 tokens per session (981 once invoked), scanned A, original, MIT.

A command that starts a coding session by reading project instructions and the latest session notes.

In plain words
What is it for?
Use it to inspect CLAUDE.md and recent .q-system/session-notes files, then report the findings before choosing the next task.
Why use it?
It restores important context before new work begins, including project rules, recent progress, and pending actions.

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-begin
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-begin

README.md
[![agentmods](https://agentmods.dev/badge/commands/contacttam/q-command-system/q-begin.svg)](https://agentmods.dev/commands/contacttam/q-command-system/q-begin)
Your own site
<a href="https://agentmods.dev/commands/contacttam/q-command-system/q-begin"><img src="https://agentmods.dev/badge/commands/contacttam/q-command-system/q-begin.svg" alt="Measured on agentmods" height="20"></a>
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 981 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 $0.00005 $0.00981
Opus 5 $0.00003 $0.00491
Sonnet 5 $0.00001 $0.00196
Haiku 4.5 $0.00001 $0.00098

Measured 3d ago against content hash c2fee8321ee9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

q-begin 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-begin.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Start Session

Purpose: Initialize a new work session with full context refresh.


MANDATORY PRE-FLIGHT CHECKLIST

STOP. Before proceeding, confirm:

  • 1. I will execute ALL 5 steps in order
  • 2. I will NOT skip reading session notes
  • 3. I will report findings to user before asking what to work on

Step 1: Read Project Context

EXECUTE:

cat CLAUDE.md 2>/dev/null || echo "No CLAUDE.md found"
  • Read CLAUDE.md completely
  • Note key policies (especially git push policy)
  • Note team members if listed
  • Note project status

If CLAUDE.md not found: Note this - it's okay to continue, but suggest running /q-setup.


Step 2: MANDATORY - Find and Read Last Session Notes

2.1 List Session Notes

ls -la .q-system/session-notes/ 2>/dev/null | tail -5 || echo "No session notes found"
  • Command executed
  • Identified most recent file

2.2 Read Last Session Notes

If session notes exist:

# Read the most recent session notes file
cat .q-system/session-notes/[MOST_RECENT_FILE]
  • File read completely
  • Noted key accomplishments
  • Noted pending "Next Actions"
  • Noted any blockers or issues

VERIFICATION GATE 1:

Last session notes: [filename or "none found"]
Key items from last session:
- Accomplishments: [list or "N/A"]
- Pending actions: [list or "N/A"]

If no session notes exist: This is the first session - note this for the summary.


Step 3: Check Current Repository Status

3.1 Git Status

git status
  • Command executed
  • Noted if working tree is clean or dirty
  • Noted any uncommitted changes

3.2 Check for Uncommitted Session Work

git diff --stat HEAD 2>/dev/null || echo "No git history"
  • Identified any uncommitted changes

3.3 Check for Orphaned Checkpoints

ls -la .q-system/checkpoints/ 2>/dev/null | tail -3 || echo "No checkpoints"
  • Noted any checkpoints from previous sessions that weren't incorporated

Read the full file on GitHub · 178 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. 3d ago First seen · 178 lines · 5 tokens per session scan A c2fee8321ee9

Subscribe to this mod's changes

q-begin is a command published in the GitHub repository contactTAM/q-command-system (5 stars, last pushed 8mo ago), licensed MIT. It adds 5 tokens to every session and 981 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 2026-08-31.