mem-search

mem-search is a skill for Claude Code, Codex from MSApps-Mobile/claude-plugins. It costs 88 tokens per session (479 once invoked), scanned A, original, MIT.

A search tool for persistent project memory, using exact keyword matching and similarity-based search to find related notes.

In plain words
What is it for?
Use it to look up previous notes about tools, files, decisions, authentication, databases, or deployment problems, then retrieve the full details of useful results.
Why use it?
It helps recover past decisions, errors, and context instead of repeating earlier investigation. The two search methods cover both exact terms and differently worded questions.

Skill for Claude CodeCodex

Part of the cowork-mem plugin — 7 skills, 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 skills/msapps-mobile/claude-plugins/mem-search
Any agent
npx skills add MSApps-Mobile/claude-plugins --skill mem-search
Clone the repo
git clone --depth 1 https://github.com/MSApps-Mobile/claude-plugins

Made for: Claude Code, Codex.

Or install cowork-mem, the plugin that ships this one along with the rest of its 7 skills, 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 mem-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/mem-search.svg)](https://agentmods.dev/skills/msapps-mobile/claude-plugins/mem-search)
Your own site
<a href="https://agentmods.dev/skills/msapps-mobile/claude-plugins/mem-search"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/mem-search.svg" alt="Measured on agentmods" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 479 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 $0.00088 $0.00479
Opus 5 $0.00044 $0.00239
Sonnet 5 $0.00018 $0.00096
Haiku 4.5 $0.00009 $0.00048

Measured 4d ago against content hash 2cbf5d6c61d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mem-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.

plugins/cowork-mem/skills/mem-search/SKILL.md · 59 lines

What it actually says

Search cowork-mem with two complementary modes — keyword FTS5 and semantic TF-IDF. Use both for important queries; keyword finds exact matches, semantic finds related ideas.

Keyword (FTS5 — fast, exact):

python3 {SKILL_DIR}/scripts/memory_store.py search "<query>" --limit 10

Semantic (TF-IDF — finds related concepts):

COWORK_MEM_DB=~/mnt/.claude/.cowork-mem/memory.db \
python3 {SKILL_DIR}/scripts/vector_search.py "<query>" --limit 10

Fetch full detail on specific results:

python3 {SKILL_DIR}/scripts/memory_store.py get obs_abc123 obs_def456

When to Use Each Mode

Mode Best for
Keyword Exact tool names, file paths, error messages
Semantic "what did we decide about auth", "any DB issues", "deployment problems"

Search Workflow

  1. Start with semantic search — it catches paraphrases
  2. If results are weak, run keyword search as a fallback
  3. For any result worth reading in full, call get <id>
  4. Synthesize what you found into 1-2 sentences before acting on it

Filter by Type

# Only past decisions
python3 {SKILL_DIR}/scripts/memory_store.py search "<query>" --type decision

# Only errors and solutions
python3 {SKILL_DIR}/scripts/memory_store.py search "<query>" --type error

Types: decision, file_edit, tool_use, insight, error, note, summary

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 · 59 lines · 88 tokens per session scan A 2cbf5d6c61d6

Subscribe to this mod's changes

mem-search is a skill published in the GitHub repository MSApps-Mobile/claude-plugins (9 stars, last pushed 8d ago), licensed MIT. It adds 88 tokens to every session and 479 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

archon

Autonomous multi-session campaign agent. Decomposes large work into phases, delegates to sub-agents, reviews output, and maintains campaign state across context windows. Use for work that spans multiple sessions and needs persistent state, quality judgment, and strategic decomposition.

SethGammon/Citadel · 54 tokens

marshal

Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.

SethGammon/Citadel · 56 tokens

wiki

Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.

SethGammon/Citadel · 56 tokens

baalda-optimizer

Framework-driven audit and optimizer for a Baalda vault. Applies 9 frameworks (F1 Anthropic CLAUDE.md, F2 Karpathy Wiki, F3 Caveman, F4 Chroma Context Rot, F5 Anthropic Memory, F6 Progressive Disclosure, G7 Hygiene, F8 Reflection, F9 Architecture & Discoverability). F9 walks the real discovery chain (root CLAUDE.md…

naveedharri/benai-skills · 237 tokens

agentic-os-obsidian

Set up an agentic OS inside an Obsidian vault — a configurable command-center dashboard with 5 auto-installed, bundled plugins (Dataview, CustomJS, Shell-commands, Terminal, Homepage), Home + per-profile + Vault Overview pages, KPI cards, sparklines, heatmap, task rollup, and a button bar wired to user-defined Claude…

naveedharri/benai-skills · 154 tokens

skill-os-builder

Stand up a self-contained second-brain "OS" that lives entirely inside a Claude skill — a short SKILL.md router plus context files, no vault, cloud, or MCP server. Use when the user says "set up a skill OS", "build my second brain as a skill", "skill OS", or wants the simplest portable AI OS.

naveedharri/benai-skills · 75 tokens