capture

capture is a command for Claude Code from DimitriGeelen/agentic-engineering-framework. It costs 0 tokens per session (599 once invoked), scanned A, original, Apache-2.0.

When the user types /capture, execute this workflow to save the current conversation to disk before it is lost.

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/dimitrigeelen/agentic-engineering-framework/capture
Clone the repo
git clone --depth 1 https://github.com/DimitriGeelen/agentic-engineering-framework

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 capture

README.md
[![agentmods](https://agentmods.dev/badge/commands/dimitrigeelen/agentic-engineering-framework/capture.svg)](https://agentmods.dev/commands/dimitrigeelen/agentic-engineering-framework/capture)
Your own site
<a href="https://agentmods.dev/commands/dimitrigeelen/agentic-engineering-framework/capture"><img src="https://agentmods.dev/badge/commands/dimitrigeelen/agentic-engineering-framework/capture.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 599 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 $0.00000 $0.00599
Opus 5 $0.00000 $0.00300
Sonnet 5 $0.00000 $0.00120
Haiku 4.5 $0.00000 $0.00060

Measured today against content hash 7f8618999320, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

capture 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 today.

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.

.claude/commands/capture.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/capture - Emergency Conversation Capture

When the user types /capture, execute this workflow to save the current conversation to disk before it is lost.

Step 1: Check active task

Read .context/working/focus.yaml to get current_task.

If no active task or current_task is empty:

  • Print: "No active task. Run fw work-on 'topic' first to create one, then retry /capture."
  • Stop here.

Step 2: Extract conversation from transcript

Run:

python3 agents/capture/read-transcript.py

This reads the live JSONL transcript and returns JSON with:

  • turns: array of {role, content, timestamp} objects
  • captured_turns: how many turns were captured
  • capture_mode: how the boundary was detected

If the script exits non-zero or returns empty turns, print the warning from stderr and stop.

Step 3: Write the artifact

Generate the artifact path:

docs/reports/{current_task}-capture-{YYYY-MM-DD-HH}.md

Write the file with this structure:

# {current_task}: Conversation Capture — {YYYY-MM-DD HH:MM}

> Captured via /capture | Turns: {captured_turns} | Mode: {capture_mode}
> Task: {current_task}

## Topic / Problem Statement

{Summarise in 2-3 sentences what this conversation is about, based on the turns.}

## Key Insights

{List the most important findings or conclusions reached, as bullet points.
Extract from the conversation content — don't hallucinate.}

## Options Explored

{If alternatives were discussed, list them with brief notes on each.
Skip this section if no options were compared.}

## Decisions Made

{List any explicit decisions or directions agreed on.
Skip if no decisions were made.}

## Open Questions

{List anything that was raised but not resolved.}

## Conversation Log

{For each turn in the turns array, format as:}

**Human** _{timestamp}_
{content}

---

**Agent** _{timestamp}_
{content}

---

Step 4: Commit

Run:

fw git commit -m "{current_task}: /capture — conversation artifact"

Step 5: Report back

Read the full file on GitHub · 106 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. today First seen · 106 lines · 0 tokens per session scan A 7f8618999320

Subscribe to this mod's changes

capture is a command published in the GitHub repository DimitriGeelen/agentic-engineering-framework (13 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 599 tokens. 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 2026-09-04.