search

A command for searching stored memories with text or meaning-based filters. It supports options for search type, namespace, and result limit.

In plain words
What is it for?
Use it with /memory:search to search memories, choose semantic or text search, restrict results to a namespace, or limit the number of results.
Why use it?
It helps find relevant saved information without searching every memory manually.

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/zircote/git-notes-memory/search
Clone the repo
git clone --depth 1 https://github.com/zircote/git-notes-memory
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 1,538 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 $0.01538
Opus 5 $0.00003 $0.00769
Sonnet 5 $0.00001 $0.00308
Haiku 4.5 $0.00001 $0.00154

Measured yesterday against content hash 20b0042300f5, 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.

commands/search.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<help_check>

Help Check

If $ARGUMENTS contains --help or -h:

Output this help and HALT (do not proceed further):

<help_output>

SEARCH(1)                                            User Commands                                            SEARCH(1)

NAME
    search - Search memories with advanced filtering options

SYNOPSIS
    /memory:search <query> [--type=semantic|text] [--namespace=ns] [--limit=n]

DESCRIPTION
    Search memories with advanced filtering options

OPTIONS
    --help, -h                Show this help message

EXAMPLES
    /memory:search
    /memory:search --help

SEE ALSO
    /memory:* for related commands

                                                                      SEARCH(1)

</help_output>

After outputting help, HALT immediately. Do not proceed with command execution. </help_check>


Search memories with advanced filtering and search options.

Your Task

You will help the user search memories with precise control over search behavior.

Arguments format: $ARGUMENTS

Parse the arguments:

  1. Extract --type=<type> if present: semantic (default) or text
  2. Extract --namespace=<ns> if present
  3. Extract --spec=<spec> if present
  4. Extract --limit=<n> if present (default: 10)
  5. Extract --verbose flag if present
  6. Everything else is the search query

If query is missing, use AskUserQuestion to prompt for it.

Use Bash to invoke the Python library:

Semantic Search (default - vector similarity):

PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-$(ls -d ~/.claude/plugins/cache/git-notes-memory/memory-capture/*/ 2>/dev/null | head -1)}"
uv run --directory "$PLUGIN_ROOT" python3 -c "
from git_notes_memory import get_recall_service

recall = get_recall_service()
results = recall.search(
    query='''$QUERY''',
    k=$LIMIT,
    namespace=$NAMESPACE,
    spec=$SPEC,
)

print(f'## Search Results for \"{'''$QUERY'''}\" ({len(results)} found)\n')
if results:
    print('| # | Namespace | Summary | Score | Date |')
    print('|---|-----------|---------|-------|------|')
    for i, r in enumerate(results, 1):
        summary = r.summary[:40].replace('|', '\\|')
        date = r.timestamp.strftime('%Y-%m-%d')
        print(f'| {i} | {r.namespace} | {summary} | {r.score:.2f} | {date} |')
else:
    print('No results found.')
"

Read the full file on GitHub · 205 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 · 205 lines · 6 tokens per session scan A 20b0042300f5

Subscribe to this mod's changes

search is a command published in the GitHub repository zircote/git-notes-memory (4 stars, last pushed 8mo ago), licensed MIT. It adds 6 tokens to every session and 1,538 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.