search

A command for searching stored memories using text or regular expressions. It can search all memories or limit results by namespace, scope, case sensitivity, context lines, or matching files.

In plain words
What is it for?
Use it to find stored information by keyword or pattern, inspect nearby matching lines, list matching files, and search user or project memories.
Why use it?
It removes the need to manually browse memory files when looking for a past note or saved detail. Filters help narrow results to the relevant project or user information.

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/modeled-information-format/mnemonic/search
Clone the repo
git clone --depth 1 https://github.com/modeled-information-format/mnemonic
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,130 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 $0.00008 $0.01130
Opus 5 $0.00004 $0.00565
Sonnet 5 $0.00002 $0.00226
Haiku 4.5 $0.00001 $0.00113

Measured yesterday against content hash e88b114b6380, 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 · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory

Search first: /mnemonic:search {relevant_keywords} Capture after: /mnemonic:capture {namespace} "{title}"

Run /mnemonic:list --namespaces to see available namespaces from loaded ontologies.

Direct ripgrep search across mnemonic memories.

Arguments

  • <pattern> - Required. Search pattern (supports regex)
  • --namespace - Limit search to specific namespace
  • --context - Lines of context around matches (default: 0)
  • --files-only - Only list matching file paths
  • --case-sensitive - Case-sensitive search (default: case-insensitive)
  • --scope - user, project, or all (default: all)

Procedure

Step 1: Parse Arguments

PATTERN="${1:?Error: Pattern required}"
NAMESPACE="${NAMESPACE:-}"
CONTEXT="${CONTEXT:-0}"
FILES_ONLY="${FILES_ONLY:-false}"
CASE_SENSITIVE="${CASE_SENSITIVE:-false}"
SCOPE="${SCOPE:-all}"

ORG=$(git remote get-url origin 2>/dev/null | sed -E 's|.*[:/]([^/]+)/[^/]+\.git$|\1|' | sed 's|\.git$||')
[ -z "$ORG" ] && ORG="default"

Step 2: Build Search Command

# Base command
RG_CMD="rg"

# Case sensitivity
[ "$CASE_SENSITIVE" = "false" ] && RG_CMD="$RG_CMD -i"

# Context lines
[ "$CONTEXT" -gt 0 ] && RG_CMD="$RG_CMD -C$CONTEXT"

# Files only
[ "$FILES_ONLY" = "true" ] && RG_CMD="$RG_CMD -l"

# File pattern
RG_CMD="$RG_CMD --glob '*.memory.md'"

Step 3: Determine Search Paths

SEARCH_PATHS=""

case "$SCOPE" in
    user)
        SEARCH_PATHS="$HOME/.claude/mnemonic/$ORG"
        ;;
    project)
        SEARCH_PATHS="./.claude/mnemonic"
        ;;
    all|*)
        SEARCH_PATHS="$HOME/.claude/mnemonic/$ORG ./.claude/mnemonic"
        ;;
esac

# Narrow by namespace
if [ -n "$NAMESPACE" ]; then
    NEW_PATHS=""
    for path in $SEARCH_PATHS; do
        [ -d "$path/$NAMESPACE" ] && NEW_PATHS="$NEW_PATHS $path/$NAMESPACE"
    done
    SEARCH_PATHS="$NEW_PATHS"
fi

Step 4: Execute Search

echo "=== Searching: $PATTERN ==="
echo ""

for path in $SEARCH_PATHS; do
    if [ -d "$path" ]; then
        if [ "$FILES_ONLY" = "true" ]; then
            rg $([[ "$CASE_SENSITIVE" = "false" ]] && echo "-i") -l "$PATTERN" "$path" --glob "*.memory.md" 2>/dev/null
        else
            rg $([[ "$CASE_SENSITIVE" = "false" ]] && echo "-i") $([[ "$CONTEXT" -gt 0 ]] && echo "-C$CONTEXT") "$PATTERN" "$path" --glob "*.memory.md" 2>/dev/null
        fi
    fi
done

Read the full file on GitHub · 179 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 · 179 lines · 8 tokens per session scan A e88b114b6380

Subscribe to this mod's changes

search is a command published in the GitHub repository modeled-information-format/mnemonic (22 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 1,130 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 2026-08-30.