export-conversation

A session command that exports the current conversation to Markdown, a plain-text document format, with extra metadata for linking it into a knowledge graph.

In plain words
What is it for?
Use it to save a full transcript, a summary, or both, choose an export location, and optionally update the daily note.
Why use it?
It gives you a saved, searchable record of the conversation and can also connect the export with a daily note.

Command

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/jonathanprozzi/claude-utils/export-conversation
Clone the repo
git clone --depth 1 https://github.com/jonathanprozzi/claude-utils
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 3,109 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.03109
Opus 5 $0.00000 $0.01554
Sonnet 5 $0.00000 $0.00622
Haiku 4.5 $0.00000 $0.00311

Measured 2d ago against content hash 7b6d664dec80, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

export-conversation scanned grade B with 1 finding 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 2d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- Alternatively, find the most recent `.jsonl` in `~/.claude/projects/` matching the current working directory
commands/export-conversation.md · 364 lines

How it starts

The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a comprehensive markdown export of this conversation session with enhanced frontmatter for knowledge graph integration.

Command Usage:

  • /export-conversation - Export using saved preferences (default: comprehensive format)
  • /export-conversation -f or --full - Export full transcript with all tool calls
  • /export-conversation -s or --summary - Export detailed summary only
  • /export-conversation -b or --both - Export both summary and full transcript
  • /export-conversation -n or --no-update - Skip daily note integration
  • /export-conversation --no-prompt - Skip all prompts, use saved defaults

Flags can be combined: /export-conversation -b (both + daily note update), /export-conversation -bn (both, skip daily note)

Configuration & Directory Selection

First, check for config at ~/.config/claude-code-workflow/config.json (primary) or ~/.claude/export-conversation-config.json (legacy):

Based on the result:

  1. If no config or savedDirectory is empty:

    • Ask: "Where would you like to save conversation exports? Options:
      • Press Enter for current directory (one-time)
      • Type a path to save there and remember for future exports
      • Type 'obsidian' to browse common Obsidian vault locations"
  2. If savedDirectory exists in config:

    • Ask: "Export to saved location: [savedDirectory]? Options:
      • Press Enter to use saved location
      • Type 'current' to use current directory (one-time)
      • Type a new path to change saved location
      • Type 'forget' to clear saved preference"

Save Configuration

When user provides a new directory path:

  1. Verify the directory exists or create it
  2. Save the preference to ~/.config/claude-code-workflow/config.json:
    {
      "savedDirectory": "USER_PROVIDED_PATH",
      "obsidian_vault_path": "/path/to/vault",
      "lastUsed": "CURRENT_DATE"
    }
    
  3. For 'forget': remove the savedDirectory key from config

Project Detection

Detect project context for frontmatter:

Read the full file on GitHub · 364 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. 2d ago First seen · 364 lines · 0 tokens per session scan B 7b6d664dec80

Subscribe to this mod's changes

export-conversation is a command published in the GitHub repository jonathanprozzi/claude-utils (11 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,109 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.