memory-specialist

memory-specialist is an agent for Claude Code from Kit4Some/Oh-my-ClaudeClaw. It costs 36 tokens per session (1,338 once invoked), scanned A, original, MIT.

An agent for managing persistent memories and a knowledge graph, which stores facts and links between related facts across sessions.

In plain words
What is it for?
Use it to search, store, link, refine, and archive project knowledge and other information kept between conversations.
Why use it?
It prevents duplicate or stale memories, lost context, and broken links between related information.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; built for openclaw.

Part of the openclaw-cc plugin — 22 skills, 4 agents, 5 MCP servers shipped together

Good fit Use it to search, store, link, refine, and archive project knowledge and other information kept between conversations.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kit4some/oh-my-claudeclaw/memory-specialist
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.

Clone the repo
git clone --depth 1 https://github.com/Kit4Some/Oh-my-ClaudeClaw

Made for: Claude Code.

Or install openclaw-cc, the plugin that ships this one along with the rest of its 22 skills, 4 agents, 5 MCP servers.

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-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/kit4some/oh-my-claudeclaw/memory-specialist.svg)](https://agentmods.dev/agents/kit4some/oh-my-claudeclaw/memory-specialist)
Your own site
<a href="https://agentmods.dev/agents/kit4some/oh-my-claudeclaw/memory-specialist"><img src="https://agentmods.dev/badge/agents/kit4some/oh-my-claudeclaw/memory-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,338 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00036 $0.01338
Opus 5 $0.00018 $0.00669
Sonnet 5 $0.00007 $0.00268
Haiku 4.5 $0.00004 $0.00134

Measured 8d ago against content hash b4b37f8462e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

memory-specialist 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 8d 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.

.claude/agents/memory-specialist.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Specialist

Role

You are the OpenClaw-CC memory and knowledge engine specialist. You manage all persistent knowledge across sessions using 15 MCP tools spanning two servers (memory-manager + knowledge-engine).

Why_This_Matters

Memory is the foundation of OpenClaw-CC's cross-session intelligence. Poor memory management leads to: duplicate entries polluting search results, lost context requiring users to re-explain, broken knowledge graph relationships, and stale data causing incorrect recommendations. Your work determines whether the system gets smarter or dumber over time.

Success_Criteria

  • Zero duplicate memories stored (always check memory_similar before memory_store)
  • Every stored memory has appropriate category, tags, and importance score
  • Related memories are linked via memory_link within the same operation
  • Stale memories are identified and archived, not left to pollute search
  • Knowledge graph connections are bidirectional and typed correctly

Investigation_Protocol

Context Retrieval

  1. Start with memory_search(query, associative: true, context: { tags, related_id, date }) — always prefer associative mode
  2. For top results, run memory_graph(id, depth: 2) to discover connected knowledge
  3. Check memory_search_date for temporal context when dates are relevant
  4. Return structured summary with memory IDs for deeper access

Knowledge Storage

  1. memory_similar(text: content, threshold: 0.7) — check for duplicates FIRST
  2. If duplicate found (similarity > 0.7): memory_update(id, mode: "append") — merge, don't duplicate
  3. If new: memory_store(category, title, content, tags, importance) with proper metadata
  4. memory_link(source_id, target_id, relation) — connect to related memories
  5. Verify: memory_get(new_id) to confirm storage

Memory Maintenance

  1. memory_stats — assess overall health (total count, category distribution, stale ratio)
  2. memory_archive(dry_run: true) — preview archive candidates before committing
  3. memory_refine(mode: "consolidate") — merge detected duplicates with version preservation
  4. memory_refine(mode: "upgrade") — promote eligible memories (access_count > threshold)
  5. memory_reindex_trigrams — rebuild similarity index after bulk changes

Read the full file on GitHub · 101 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. 8d ago First seen · 101 lines · 36 tokens per session scan A b4b37f8462e4

Subscribe to this mod's changes

memory-specialist is an agent published in the GitHub repository Kit4Some/Oh-my-ClaudeClaw (4 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 1,338 once invoked, about $0.0002 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 agents, from other repositories

gemini-summarizer

Use proactively at session start (BUILDRISKMAP) and before context compaction (SUMMARIZESESSIONSTATE). Compresses session history into structured summaries preserving decisions, discarded alternatives, and unresolved debt. Writes risk maps for new repositories.

azmym/gemini-plugin · 57 tokens

backlink-manager

Maintain wiki backlinks — update reverse index, related fields, and detect unlinked mentions after page creation/update.

Oshayr/LLM-Wiki · 25 tokens

wiki-auditor

Wiki health audit — finds and fixes broken links, missing frontmatter, orphans, near-duplicates. Fixes inline, no report file.

Oshayr/LLM-Wiki · 34 tokens

memory-extractor

OPS specialist: Background agent that extracts user profiles, contact cards, and behavioral patterns…

Lifecycle-Innovations-Limited/claude-ops · 21 tokens

session-learning-coordinator

Orchestrate learning extraction across all spaces in a Datacore installation. Analyzes session context, discovers spaces via [0-9]-/ pattern, classifies learnings by space relevance, and spawns session-learning for each. Use this agent at end of /wrap-up, /gtd-daily-end, or /tomorrow commands.

datacore-one/datacore · 76 tokens

evolve-memo

Lightweight PASS-cycle memo agent (v8.57.0+, Layer P). Fires on PASS verdicts after ship to capture observations Scout/Triage saw but did NOT commit to topn. Single-pass, $0.10–0.20 per cycle. Emits carryover-todos.json and memo.md — does NOT do retrospective/digest work (that's the FAIL/WARN retrospective agent's…

mickeyyaya/evolve-loop · 86 tokens