recall

A command for retrieving related information from a knowledge graph, which stores connected facts and past decisions.

In plain words
What is it for?
Use it to recall general information, task-specific decisions, or a deeper set of related project facts.
Why use it?
It avoids manually searching through previous project knowledge when you need context for a question or task.

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/tm42/mnemograph/recall
Clone the repo
git clone --depth 1 https://github.com/tm42/mnemograph
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 312 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 $0.00010 $0.00312
Opus 5 $0.00005 $0.00156
Sonnet 5 $0.00002 $0.00062
Haiku 4.5 $0.00001 $0.00031

Measured 2d ago against content hash 6d00db7b45d7, 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 2d 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.

mnemograph-claude-code/commands/recall.md · 36 lines

What it actually says

Recall from Knowledge Graph

Use the mnemograph MCP server to retrieve relevant context from the knowledge graph.

Your Task

The user wants to recall information. Their query: $ARGUMENTS

Instructions

  1. Determine recall depth based on the query:

    • If the query is a quick orientation question (e.g., "what's in memory?", "overview") → use depth: shallow
    • If the query is task-specific (e.g., "auth decisions", "API patterns") → use depth: medium
    • If the query needs deep exploration (e.g., "everything about X", "full context") → use depth: deep
  2. Call the mnemograph recall tool with:

    • query: The user's query (use $ARGUMENTS)
    • depth: As determined above
    • format: "prose" for human-readable output
  3. Present the results clearly:

    • Summarize the key entities and their relationships
    • Highlight any decisions or learnings that are relevant
    • If the query found nothing useful, suggest what topics might exist

Example Queries

  • /recall auth → medium depth search for authentication-related knowledge
  • /recall → shallow overview of what's in the graph
  • /recall everything about the API design → deep exploration
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. 2d ago First seen · 36 lines · 10 tokens per session scan A 6d00db7b45d7

Subscribe to this mod's changes

recall is a command published in the GitHub repository tm42/mnemograph (2 stars, last pushed 6mo ago), licensed MIT. It adds 10 tokens to every session and 312 once invoked, about $0.0001 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.