q-dump

q-dump is a command for Claude Code from contactTAM/q-command-system. It costs 4 tokens per session (476 once invoked), scanned A, original, MIT.

A command that manually saves a written record of the entire coding session, including work before an automatic context reset.

In plain words
What is it for?
Use it to create a dated Markdown transcript in .q-system/transcripts for later review or handoff.
Why use it?
It preserves the conversation and progress when the normal session-ending process is not needed or cannot be used.

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-dump
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-dump

README.md
[![agentmods](https://agentmods.dev/badge/commands/contacttam/q-command-system/q-dump.svg)](https://agentmods.dev/commands/contacttam/q-command-system/q-dump)
Your own site
<a href="https://agentmods.dev/commands/contacttam/q-command-system/q-dump"><img src="https://agentmods.dev/badge/commands/contacttam/q-command-system/q-dump.svg" alt="Measured on agentmods" height="20"></a>
Per session 4 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 476 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 $0.00004 $0.00476
Opus 5 $0.00002 $0.00238
Sonnet 5 $0.00001 $0.00095
Haiku 4.5 $0.00000 $0.00048

Measured 3d ago against content hash 63e49d052d6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

q-dump 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-dump.md · 98 lines

What it actually says

Dump Session Transcript

Purpose: Create a session transcript without the full /q-end workflow.

Step 1: Check for Continued Sessions

  1. Look for: "This session is being continued from a previous conversation"
  2. If present, the conversation summary contains work before auto-compact
  3. You MUST document the ENTIRE session (summary + current context)

Step 2: Determine Session Start Time

  • Regular session: Use current session start time
  • Continued session: Use ORIGINAL session start time from summary

Step 3: Generate Timestamp

TIMESTAMP=$(date +"%Y-%m-%d-%H%M")

Step 4: Create Transcript Directory

mkdir -p .q-system/transcripts

Step 5: Determine Participant Name

Use known name or ask user.

Step 6: Create Transcript File

Create .q-system/transcripts/${TIMESTAMP}-[Name].md:

# Session Transcript: [TIMESTAMP]

**Date:** [YYYY-MM-DD]
**Participant:** [Name]
**Duration:** [X hours Y minutes]
**Type:** [Regular / Continued from auto-compact]

---

## Session Flow

### [Time] - [Topic/Task]

[Description of what was discussed/done]

### [Time] - [Topic/Task]

[Description of what was discussed/done]

[Continue chronologically...]

---

## Summary

### Accomplishments
- [Bullet list]

### Files Changed
- Created: [list]
- Modified: [list]

### Key Decisions
- [Decision]: [Rationale]

### Metrics
- Duration: [X hours Y minutes]
- Files changed: [N]
- Commits: [N]

Step 7: Verify and Report

VERIFY: File exists and has substantial content (>50 lines for real sessions)

Transcript created: .q-system/transcripts/[filename]
  - Duration: [X hours Y minutes]
  - [N] lines documented

Difference from /q-end:

  • /q-dump: Only creates transcript
  • /q-end: Creates transcript + session notes + commits
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 · 98 lines · 4 tokens per session scan A 63e49d052d6f

Subscribe to this mod's changes

q-dump is a command published in the GitHub repository contactTAM/q-command-system (5 stars, last pushed 8mo ago), licensed MIT. It adds 4 tokens to every session and 476 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.