recall

A command that searches a local graph-based memory and returns a small, source-linked answer.

In plain words
What is it for?
Answering questions from local project memory and citing the documents that support the result.
Why use it?
It helps an agent find relevant stored facts without loading whole documents or guessing when the memory has no reliable answer.

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/gru-953/mta_plugin/recall
Clone the repo
git clone --depth 1 https://github.com/GRU-953/MTA_Plugin
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 194 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 $0.00017 $0.00194
Opus 5 $0.00009 $0.00097
Sonnet 5 $0.00003 $0.00039
Haiku 4.5 $0.00002 $0.00019

Measured today against content hash cc194be8f1c7, 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 today.

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 · 19 lines

What it actually says

Answer the user's question from local memory using the recall tool.

Question: $ARGUMENTS

Steps:

  1. Call recall with the question (and project if the user named one).
  2. It runs a local, model-free BM25 keyword search and returns a small relevant slice — theme summaries and entity cards with their source documents. It never returns whole documents.
  3. Answer the user's question grounded in those hits, citing the source document names where provided. If status is no_memory, suggest running /memorise first.
  4. If the result has low_confidence: true (or no hits clear the relevance floor), tell the user the memory doesn't contain a confident answer rather than guessing.
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. today First seen · 19 lines · 17 tokens per session scan A cc194be8f1c7

Subscribe to this mod's changes

recall is a command published in the GitHub repository GRU-953/MTA_Plugin (1 stars, last pushed 26d ago), licensed MIT. It adds 17 tokens to every session and 194 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.