clean

A cleanup command for removing old or unwanted saved conversation files after confirmation.

In plain words
What is it for?
It is for deleting files before a chosen date, keeping only a selected number of recent files, or previewing deletions with a dry run.
Why use it?
It helps reduce clutter in the directory where exported chats accumulate.

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/dropfan/claude-code-plugins/clean
Clone the repo
git clone --depth 1 https://github.com/DropFan/claude-code-plugins
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 642 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 $0.00006 $0.00642
Opus 5 $0.00003 $0.00321
Sonnet 5 $0.00001 $0.00128
Haiku 4.5 $0.00001 $0.00064

Measured yesterday against content hash 0d041003e147, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clean 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 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.

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.

plugins/chat-saver/commands/clean.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 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

Clean up old or unwanted saved conversation files with user confirmation.

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: save_dir.

Step 1: Parse Arguments

Parse optional arguments from $ARGUMENTS:

  • --before YYYY-MM-DD — Delete files with a date prefix before the specified date
  • --keep N — Keep the N most recent files, delete the rest
  • --dry-run — Preview which files would be deleted without actually deleting them

If no arguments are provided, use AskUserQuestion to let the user choose a mode:

  • By date — Delete files older than a specific date
  • Keep recent — Keep the N most recent files
  • Select manually — Show all files and let the user pick which to delete

Step 2: Scan and Filter

  1. Use Glob to find all files in <save_dir> (*.md, *.txt, *.html)
  2. Extract the date prefix from each filename
  3. Apply the selected filter:
    • --before: Compare filename date prefix against the cutoff date
    • --keep: Sort by date (newest first), mark all beyond the Nth file for deletion
    • Manual: Display all files and use AskUserQuestion for selection

Step 3: Preview

Display the files that will be deleted:

Files to delete:

  1. 2024-01-10-old-topic.md (45 lines, 3K)
  2. 2024-01-08-another-topic.txt (89 lines, 6K)

Total: 2 files, ~9K

If --dry-run is set, display the preview and stop here without deleting.

Step 4: Confirm

This step is mandatory — never skip confirmation.

Use AskUserQuestion to confirm:

  • Delete — Proceed with deletion
  • Cancel — Abort without deleting

Step 5: Delete

Delete each file individually using rm (one file per command, no wildcards):

rm <save_dir>/2024-01-10-old-topic.md

Read the full file on GitHub · 84 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. yesterday First seen · 84 lines · 6 tokens per session scan A 0d041003e147

Subscribe to this mod's changes

clean is a command published in the GitHub repository DropFan/claude-code-plugins (7 stars, last pushed 26d ago), licensed MIT. It adds 6 tokens to every session and 642 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.