agent-memory

A command for searching and managing locally stored agent memories, including indexed code information.

In plain words
What is it for?
Use it to search, add, list, retrieve, index, summarise, and ask questions about memories, or inspect code trees and cross-references.
Why use it?
It helps find earlier notes and navigate indexed code without using external services for its core features.

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/ruizrica/toolkit/agent-memory
Clone the repo
git clone --depth 1 https://github.com/ruizrica/toolkit
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,721 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 $0.00000 $0.01721
Opus 5 $0.00000 $0.00860
Sonnet 5 $0.00000 $0.00344
Haiku 4.5 $0.00000 $0.00172

Measured 2d ago against content hash f6ec8d12b102, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-memory 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.

docs/commands/agent-memory.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/agent-memory

ABOUTME: Documentation for the /agent-memory command — hybrid search over agent memory files. ABOUTME: Covers usage, arguments, architecture, search modes, examples, and setup.

Search and manage the local agent memory system using hybrid search. Fully local — zero API calls for core features.

Usage

/agent-memory <subcommand> [args]

Subcommands

Subcommand Description
search <query> Search memories (hybrid by default)
index Reindex all memory files
status Show database status
add <content> Add a memory manually
get <id> Get a memory by chunk ID
list List stored memories
ask <question> Q&A over memories (requires ANTHROPIC_API_KEY)
summarize Consolidate daily logs (requires ANTHROPIC_API_KEY)
install Download embedding model (~67MB)
code-index <path> Build code tree from a codebase
code-nav <query> Navigate code tree to find relevant code
code-tree Display indexed code tree structure
code-refs <node-id> Show cross-references for a code node
code-summarize Generate summaries for indexed code nodes

Arguments

code-index

Argument Required Description
path Yes Root path of the codebase to index

code-nav

Argument Required Description
query Yes Search query for navigation
--json No JSON output (includes nodes + navigation trace)

code-tree

Argument Required Description
path No Filter by file path
--json No JSON output

code-refs

Argument Required Description
node_id Yes Node ID to show references for
--json No JSON output

search

Argument Required Description
query Yes Search query text
--vector No Vector-only search (semantic similarity)
--keyword No BM25-only search (exact term matching)
--limit N No Max results (default: 5)
--json No JSON output

Read the full file on GitHub · 220 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. 2d ago First seen · 220 lines · 0 tokens per session scan A f6ec8d12b102

Subscribe to this mod's changes

agent-memory is a command published in the GitHub repository ruizrica/toolkit (5 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,721 tokens. 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.