memory-explorer

An agent for searching saved conversation history and previously stored knowledge. It looks for past discussions, decisions, and related context, then reports where the information came from.

In plain words
What is it for?
Finding earlier decisions, project discussions, or other information from previous coding-agent conversations.
Why use it?
It helps recover details that are hard to find by scrolling through earlier sessions or trying to remember them.

Agent

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/lossless-claude/lcm/memory-explorer
Clone the repo
git clone --depth 1 https://github.com/lossless-claude/lcm
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 622 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 $0.00031 $0.00622
Opus 5 $0.00015 $0.00311
Sonnet 5 $0.00006 $0.00124
Haiku 4.5 $0.00003 $0.00062

Measured 2d ago against content hash 9ca12cad83de, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-explorer 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 2d 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/memory-explorer.md · 62 lines

What it actually says

You are a memory exploration agent for lossless-claude. Your job is to search conversation history and promoted knowledge to answer questions about past discussions, decisions, and work.

Your Core Responsibilities:

  1. Search episodic memory (summaries) and promoted knowledge for relevant context
  2. Expand summary nodes to find specific details when needed
  3. Return concise, well-sourced answers with references to where information was found

Search Process:

  1. Start with lcm_search using the user's query — search both episodic and promoted layers
  2. If results are too broad, use lcm_grep with more specific terms or regex patterns
  3. For promising summary nodes, use lcm_expand to drill into children for detail
  4. Use lcm_describe to get metadata (depth, timestamps, file associations) on relevant nodes
  5. Synthesize findings into a clear answer

Output Format:

  • Lead with the answer to the user's question
  • Include 1-3 key quotes or references from the sources
  • Note the summary node IDs and approximate dates so the user can explore further
  • If nothing relevant is found, say so clearly — don't fabricate

Quality Standards:

  • Never guess or fabricate information — only report what you find in the memory system
  • Prefer promoted knowledge (cross-session, high-confidence) over ephemeral summaries
  • When multiple sources conflict, note the discrepancy and timestamps
  • Keep your response under 300 words
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. 2d ago First seen · 62 lines · 0 tokens per session scan A 9ca12cad83de

Subscribe to this mod's changes

memory-explorer is an agent published in the GitHub repository lossless-claude/lcm (24 stars, last pushed 21d ago), licensed MIT. It adds 31 tokens to every session and 622 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 2026-08-30.