sm-search

sm-search is a command for coding agents from dzmitrys-dev/supamem. It costs 16 tokens per session (208 once invoked), scanned A, original, MIT.

A command for semantic search across Supamem's stored project memory. Semantic search finds related meaning, not just exact words.

In plain words
What is it for?
Searching documented codebase knowledge with queries such as billing webhook verification, payment retries, or middleware order.
Why use it?
It supplies relevant project context without starting a file edit, which helps when exploring existing patterns or checking what information an edit would receive automatically.

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/dzmitrys-dev/supamem/sm-search
Clone the repo
git clone --depth 1 https://github.com/dzmitrys-dev/supamem

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 sm-search

README.md
[![agentmods](https://agentmods.dev/badge/commands/dzmitrys-dev/supamem/sm-search.svg)](https://agentmods.dev/commands/dzmitrys-dev/supamem/sm-search)
Your own site
<a href="https://agentmods.dev/commands/dzmitrys-dev/supamem/sm-search"><img src="https://agentmods.dev/badge/commands/dzmitrys-dev/supamem/sm-search.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 208 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 $0.00016 $0.00208
Opus 5 $0.00008 $0.00104
Sonnet 5 $0.00003 $0.00042
Haiku 4.5 $0.00002 $0.00021

Measured 4d ago against content hash 8f769cf37368, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sm-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 4d 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.

src/supamem/share/commands/sm-search.md · 34 lines

What it actually says

Search the project's dual-memory corpus for relevant chunks.

Usage

/sm-search <query>

Behind the scenes this calls supamem hook claude-code with a synthetic file path to derive the query, then injects the top-k chunks into the conversation.

Examples

  • /sm-search billing webhook signature verification
  • /sm-search how do we handle Yookassa retries
  • /sm-search auth0 session middleware order

When to use

  • You want semantic context without triggering an Edit (no file path needed)
  • You want to verify what supamem will inject before making a change
  • You're exploring the codebase's documented patterns

For automatic injection on Edit/Write, the PreToolUse hook installed by supamem install --client claude-code already runs — no manual /sm-search needed.

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. 4d ago First seen · 34 lines · 16 tokens per session scan A 8f769cf37368

Subscribe to this mod's changes

sm-search is a command published in the GitHub repository dzmitrys-dev/supamem (12 stars, last pushed 14d ago), licensed MIT. It adds 16 tokens to every session and 208 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 2026-08-30.