memory-search

memory-search is a command for coding agents from PedroMosquera/squadai. It costs 12 tokens per session (264 once invoked), scanned A, original, MIT.

A command that searches a project's stored notes for earlier decisions, lessons, and incidents. It returns matching notes with relevance scores and short excerpts.

In plain words
What is it for?
Use it to find decisions about architecture, authentication, databases, or other project topics. It can also point you to a small number of notes to read in full.
Why use it?
Important project context can be spread across many memory files and be hard to find. This command helps locate past knowledge without opening every note.

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/pedromosquera/squadai/memory-search
Clone the repo
git clone --depth 1 https://github.com/PedroMosquera/squadai

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for memory-search

README.md
[![agentmods](https://agentmods.dev/badge/commands/pedromosquera/squadai/memory-search.svg)](https://agentmods.dev/commands/pedromosquera/squadai/memory-search)
Your own site
<a href="https://agentmods.dev/commands/pedromosquera/squadai/memory-search"><img src="https://agentmods.dev/badge/commands/pedromosquera/squadai/memory-search.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 264 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 5.1 $0.00012 $0.00264
Opus 5 $0.00006 $0.00132
Sonnet 5 $0.00002 $0.00053
Haiku 4.5 $0.00001 $0.00026

Measured 5d ago against content hash 2f0988a89f58, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

memory-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 5d 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.

internal/assets/commands/memory-search.md · 32 lines

What it actually says

Search project memory for entries matching the query.

The query is: $ARGUMENTS

If no query was provided, ask the user: "What are you looking for in project memory?"

Run:

squadai memory search "$ARGUMENTS" --json

Parse the JSON results and format them as a numbered list:

1. [0.82] docs/memory/auth/jwt-decision.md: We chose HS256 because the service is stateless…
2. [0.74] docs/memory/infra/db-migration.md: Migrations run at startup via golang-migrate…
3. [0.61] docs/memory/_inbox/payment-retry.md: Draft — exponential backoff for payment retries…

Each line: <rank>. [<score>] <path>: <first non-empty line of the note body>

If results are found, offer: "Would you like me to read any of these in full?" Read only the files the user requests (one or two at most).

If no results are returned, say: No entries found in docs/memory/ matching "<query>". Consider running /memory-add to capture something new.

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. 5d ago First seen · 32 lines · 12 tokens per session scan A 2f0988a89f58

Subscribe to this mod's changes

memory-search is a command published in the GitHub repository PedroMosquera/squadai (8 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 264 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.