search

A command for searching saved AI conversation files by keyword, date, or tag. Tags are labels stored in conversation metadata, such as YAML fields or HTML metadata.

In plain words
What is it for?
Use it to find saved chats containing a phrase, chats from a particular date range, or chats marked with a specific tag.
Why use it?
It avoids manually opening many saved conversations when looking for an old discussion, while allowing the search to be narrowed to a time period or label.

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/search
Clone the repo
git clone --depth 1 https://github.com/DropFan/claude-code-plugins
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 830 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 $0.00007 $0.00830
Opus 5 $0.00003 $0.00415
Sonnet 5 $0.00001 $0.00166
Haiku 4.5 $0.00001 $0.00083

Measured yesterday against content hash 68b248cdb66f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

search 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/search.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 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

Search through saved conversation files for specific keywords, optionally filtered by date range.

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 arguments from $ARGUMENTS:

  • keyword (required, unless --tag is used) — The search term or phrase to find
  • --date YYYY-MM-DD — Search only in files from a specific date
  • --from YYYY-MM-DD --to YYYY-MM-DD — Search within a date range
  • --tag — Filter results to files containing the specified tag in their metadata (YAML frontmatter tags: field, HTML <meta name="keywords">, or plain text Tags: header line)

If no keyword and no --tag is provided, use AskUserQuestion to ask for a keyword.

When --tag is used without a keyword, list all files matching the tag (no content search needed — just check metadata). When used with a keyword, first filter by tag, then search within matching files.

Step 2: Find Target Files

  1. Use Glob to scan <save_dir> for all conversation files (*.md, *.txt, *.html)
  2. If no files exist, inform the user and exit
  3. Apply filters if specified:
    • --date: Only include files whose filename starts with the exact date
    • --from/--to: Include files whose filename date falls within the range (inclusive)
    • Date comparison is based on the YYYY-MM-DD prefix in filenames
    • --tag: Use Grep to search for the tag in file metadata. For .md files, search for the tag in the YAML frontmatter tags: line. For .html files, search in the <meta name="keywords"> tag. For .txt files, search in the Tags: header line. Only keep files that contain the specified tag.

Step 3: Search Content

  1. Use Grep to search for the keyword in the filtered files:
    • Use case-insensitive matching
    • Include 2 lines of context before and after each match (-C 2)
    • Use output_mode: "content" to show matching lines
  2. Collect all matches grouped by file

Read the full file on GitHub · 79 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 · 79 lines · 7 tokens per session scan A 68b248cdb66f

Subscribe to this mod's changes

search is a command published in the GitHub repository DropFan/claude-code-plugins (7 stars, last pushed 26d ago), licensed MIT. It adds 7 tokens to every session and 830 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.