recall

A command for searching and reopening saved memories from a mnemonic filesystem, with filters for text, namespace, tags, time, type, and scope.

In plain words
What is it for?
Use it to revisit project knowledge, recent incidents, blockers, runbooks, patterns, or migrations by keyword and filters.
Why use it?
It removes the need to remember where a past decision, incident, session, or procedure was stored. You can request summaries or full content and limit the number of results.

Command

Part of the mnemonic plugin — 10 skills, 14 commands, 4 agents, 1 hook, 1 plugin shipped together

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/recall
Clone the repo
git clone --depth 1 https://github.com/modeled-information-format/mnemonic

Or install mnemonic, the plugin that ships this one along with the rest of its 10 skills, 14 commands, 4 agents, 1 hook, 1 plugin.

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 1,770 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 $0.00009 $0.01770
Opus 5 $0.00005 $0.00885
Sonnet 5 $0.00002 $0.00354
Haiku 4.5 $0.00001 $0.00177

Measured 3d ago against content hash 5e7c1807bb10, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

recall 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 3d ago.

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/recall.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 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.

/mnemonic:recall

Search and recall memories from the mnemonic filesystem.

Arguments

  • [query] - Optional search term for full-text search
  • --namespace - Filter by namespace (_semantic/decisions, _semantic/knowledge, _semantic/entities, _episodic/incidents, _episodic/sessions, _episodic/blockers, _procedural/runbooks, _procedural/patterns, _procedural/migrations)
  • --tags - Filter by tags (comma-separated)
  • --since - Time filter (7d, 30d, 90d, 1y)
  • --type - Filter by cognitive type (semantic, episodic, procedural)
  • --scope - project, org, or all (default: all)
  • --limit - Maximum results (default: 10)
  • --full - Show full memory content instead of summary

Procedure

Step 1: Parse Arguments

QUERY="${1:-}"
NAMESPACE="${NAMESPACE:-}"
TAGS="${TAGS:-}"
SINCE="${SINCE:-}"
TYPE="${TYPE:-}"
SCOPE="${SCOPE:-all}"
LIMIT="${LIMIT:-10}"
FULL="${FULL:-false}"

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 Paths

SEARCH_PATHS=""

# Get project name from git remote or directory
PROJECT=$(git remote get-url origin 2>/dev/null | sed -E 's|.*/([^/]+)\.git$|\1|' | sed 's|\.git$||')
[ -z "$PROJECT" ] && PROJECT=$(basename "$(pwd)")

# All memories are under ${MNEMONIC_ROOT}/
# Path structure:
#   {org}/{project}/ - project-specific memories
#   {org}/ - org-wide memories (shared across projects)
#   default/ - fallback when org detection fails
case "$SCOPE" in
    project)
        SEARCH_PATHS="$HOME/.claude/mnemonic/$ORG/$PROJECT"
        ;;
    org)
        SEARCH_PATHS="$HOME/.claude/mnemonic/$ORG"
        ;;
    all|*)
        # Search project-specific, then org-wide, then default
        SEARCH_PATHS="$HOME/.claude/mnemonic/$ORG/$PROJECT $HOME/.claude/mnemonic/$ORG $HOME/.claude/mnemonic/default"
        ;;
esac

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

Read the full file on GitHub · 242 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. 3d ago First seen · 242 lines · 9 tokens per session scan A 5e7c1807bb10

Subscribe to this mod's changes

recall is a command published in the GitHub repository modeled-information-format/mnemonic (22 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 1,770 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.