A command for saving the current conversation to Notion or Feishu, a document and collaboration platform.

It exports either the full conversation or a summary after checking the selected platform’s available connection.

It removes the need to copy conversation content manually into another workspace.

export — Command by DropFan

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/dropfan/claude-code-plugins/export

Clone the repo

git clone --depth 1 https://github.com/DropFan/claude-code-plugins

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 962 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.

Model	Per session	Once invoked
Fable 5	$0.00009	$0.00962
Opus 5	$0.00005	$0.00481
Sonnet 5	$0.00002	$0.00192
Haiku 4.5	$0.00001	$0.00096

Measured yesterday against content hash 4546bafaf7df, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

export 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 yesterday.

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 MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

- For Notion: add `@notionhq/notion-mcp-server` to project or global `.mcp.json` with `NOTION_TOKEN`

plugins/chat-saver/commands/export.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context

Working directory: !pwd
Current date: !date '+%Y-%m-%d %H:%M'
Plugin root: ${CLAUDE_PLUGIN_ROOT}

Task

Export the current conversation to an external platform (Notion or Feishu/飞书) via MCP integration.

User arguments: $ARGUMENTS

Step 0: Load Settings

Load settings from .claude/chat-saver.local.md following ${CLAUDE_PLUGIN_ROOT}/skills/conversation-export/references/settings-loading.md. Extract: default_scope, save_dir, custom_footer.

Step 1: Parse Arguments

Parse arguments from $ARGUMENTS:

platform (required) — notion or feishu
scope — full (default) or summary

If no platform is specified, use AskUserQuestion to let the user choose:

Notion — Export to a Notion page
Feishu (飞书) — Export to a Feishu document

Step 2: Check MCP Availability

This plugin does not ship its own MCP servers. It relies on MCP servers already configured in the user's environment (project .mcp.json, or global ~/.claude/.mcp.json).

Detect available MCP tools by checking for tools matching these patterns:

Notion: tools matching mcp__*notion* (e.g., mcp__notion-mcp__*, mcp__notion__*)
Feishu: tools matching mcp__*feishu* or mcp__*lark* (e.g., mcp__feishu-mcp__*, mcp__lark__*)

If no matching MCP tools are found for the selected platform:

Inform the user that no MCP server for the platform was detected
Provide setup instructions:
- For Notion: add @notionhq/notion-mcp-server to project or global .mcp.json with NOTION_TOKEN
- For Feishu: add a Feishu MCP server (SSE or stdio) to .mcp.json
Refer them to ${CLAUDE_PLUGIN_ROOT}/skills/conversation-export/references/mcp-export-guide.md for detailed setup steps
Offer to save locally instead (fall back to save-chat)

Step 3: Determine Topic

Same as save-chat: Analyze the conversation to extract the main topic (2-4 keywords in kebab-case).

Step 4: Generate Content

Generate the conversation content in Markdown format (the universal intermediate format for MCP export):

Read the full file on GitHub · 100 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.

yesterday First seen · 100 lines · 9 tokens per session scan B 4546bafaf7df

Subscribe to this mod's changes

export is a command published in the GitHub repository DropFan/claude-code-plugins (7 stars, last pushed 26d ago), licensed MIT. It adds 9 tokens to every session and 962 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Code review Documents Productivity ai-coding ai-coding-assistant claude-code claude-code-plugins claude-code-plugins-marketplace claude-code-skills

export

Getting it into your agent

What it costs to keep this loaded

Grade B, and why

Reads MCP configurationmediumAgent snooping

How it starts

Context

Task

Step 0: Load Settings

Step 1: Parse Arguments

Step 2: Check MCP Availability

Step 3: Determine Topic

Step 4: Generate Content

What this file has done since we first saw it

Other commands, from other repositories

prompt

full

status

csv-to-numbers

rust-critique

dotnet-structure