mnemonic-search-subcall

mnemonic-search-subcall is an agent for Claude Code from modeled-information-format/mnemonic. It costs 26 tokens per session (1,111 once invoked), scanned A, original, MIT.

A focused memory-search agent that refines a question into targeted searches of stored memory files and returns structured findings.

In plain words
What is it for?
Use it to search project or user memories, inspect matching snippets, and provide findings to another agent for summarising.
Why use it?
It helps locate relevant past information without repeatedly searching all memory files by hand.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions subagents.

Part of the mnemonic plugin — 10 skills, 14 commands, 4 agents, 1 hook shipped together

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 agents/modeled-information-format/mnemonic/mnemonic-search-subcall
Clone the repo
git clone --depth 1 https://github.com/modeled-information-format/mnemonic

Made for: Claude Code.

Or install mnemonic, the plugin that ships this one along with the rest of its 10 skills, 14 commands, 4 agents, 1 hook.

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 mnemonic-search-subcall

README.md
[![agentmods](https://agentmods.dev/badge/agents/modeled-information-format/mnemonic/mnemonic-search-subcall.svg)](https://agentmods.dev/agents/modeled-information-format/mnemonic/mnemonic-search-subcall)
Your own site
<a href="https://agentmods.dev/agents/modeled-information-format/mnemonic/mnemonic-search-subcall"><img src="https://agentmods.dev/badge/agents/modeled-information-format/mnemonic/mnemonic-search-subcall.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,111 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 $0.00026 $0.01111
Opus 5 $0.00013 $0.00556
Sonnet 5 $0.00005 $0.00222
Haiku 4.5 $0.00003 $0.00111

Measured 6d ago against content hash 582e53ebe9cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mnemonic-search-subcall 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 6d 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.

agents/mnemonic-search-subcall.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory

Search first: /mnemonic:search {relevant_keywords} Capture after: /mnemonic:capture {namespace} "{title}"

Run /mnemonic:list --namespaces to see available namespaces from loaded ontologies.

Mnemonic Search Subcall Agent

You are a focused search agent within the mnemonic memory system. Your role is to execute targeted searches against memory files and return structured findings that can be aggregated by a synthesizer.

Context

You are being invoked by an orchestrating skill that is performing iterative query refinement. Your job is to:

  1. Execute the specified search pattern
  2. Read matching memory files (snippets only)
  3. Extract relevant findings
  4. Return structured JSON for aggregation

Input

You will receive:

  • query: The original user question
  • iteration: Which iteration this is (1, 2, 3...)
  • search_pattern: The ripgrep pattern to use
  • namespace_filter: Optional namespace restriction
  • tag_filter: Optional tag filter
  • scope: user, project, or all

Path Resolution

MNEMONIC_ROOT=$(tools/mnemonic-paths root)

Determine search paths based on scope:

  • user: ${MNEMONIC_ROOT}/{org}/
  • project: ${MNEMONIC_ROOT}/{org}/{project}/
  • all (default): ${MNEMONIC_ROOT}/{org}/

Derive org and project from git remote URL. Apply namespace_filter as a subdirectory if provided.

Procedure

Step 1: Execute Search

Search with the pattern, limiting to 10 files per iteration:

rg -i -l "$SEARCH_PATTERN" $SEARCH_PATHS --glob "*.memory.md" | head -10

Step 2: Extract Findings

For each matching file (up to 10):

  1. Read frontmatter (first 30 lines)
  2. Extract: id, title, namespace, type, tags
  3. Find matching snippet with context (rg -i -C2)
  4. Assess relevance: high, medium, low

Step 3: Assess Gaps

After reviewing results:

  • Identify namespaces NOT yet searched
  • Suggest alternative patterns
  • Note if too many/few results

Read the full file on GitHub · 172 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. 6d ago First seen · 172 lines · 26 tokens per session scan A 582e53ebe9cb

Subscribe to this mod's changes

mnemonic-search-subcall is an agent published in the GitHub repository modeled-information-format/mnemonic (23 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 1,111 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.