Borrowing it
Nothing to install: this file belongs to jmeyer1980/neurodivergent-memory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jmeyer1980/neurodivergent-memory/main/.github/prompts/explore_memory_city.prompt.mdgit clone --depth 1 https://github.com/jmeyer1980/neurodivergent-memoryWrote 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.
[](https://agentmods.dev/commands/jmeyer1980/neurodivergent-memory/explore_memory_city)<a href="https://agentmods.dev/commands/jmeyer1980/neurodivergent-memory/explore_memory_city"><img src="https://agentmods.dev/badge/commands/jmeyer1980/neurodivergent-memory/explore_memory_city/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/jmeyer1980/neurodivergent-memory/explore_memory_city"><img src="https://agentmods.dev/badge/commands/jmeyer1980/neurodivergent-memory/explore_memory_city.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00037 | $0.00556 |
| Opus 5.5 | $0.00015 | $0.00222 |
| Sonnet 5.5 | $0.00007 | $0.00111 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
explore_memory_city 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 1mo 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.
What it actually says
You are exploring the neurodivergent-memory MCP server itself, not merely describing it.
Inputs:
- {{input}}: Optional focus for the exploration, such as a topic, district, tag, memory id, or a freeform goal like "show me what has been stored about release planning".
Goal: Use the neurodivergent-memory MCP tools to literally explore the current memory graph as a "memory city" and report what you find.
Execution rules:
- Prefer direct MCP exploration over codebase explanation.
- Start by establishing current state with
memory_statsorlist_memories. - If {{input}} names a topic, tag, district, or question, use
search_memoriesto find the most relevant entries. - If a specific memory looks central, use
related_toortraverse_fromto explore its neighborhood. - Treat districts as city neighborhoods. Explain what each visited district appears to contain based on actual stored memories.
- If the memory city is sparse or empty, say so plainly and report the current counts instead of inventing structure.
- If the current client exposes this prompt but does not provide the neurodivergent-memory MCP tools, stop and say that the prompt requires that MCP server to be connected in the current agent session.
Suggested workflow:
- Call
memory_statsto assess the overall city. - Call
list_memoriesfor a broad first pass when needed. - Call
search_memoriesusing {{input}} when a focus is provided. - Call
retrieve_memory,related_to, ortraverse_fromto inspect important hubs. - Synthesize a readable tour of the city grounded in the actual results.
Output format:
- City status: <memory counts, district coverage, notable density>
- Tour route:
- Key findings: <major themes, patterns, or notable memories>
- Connections:
- Gaps: <empty districts, thin areas, or unanswered questions>
- Next exploration: <1-3 concrete follow-up queries or paths>
Style:
- Be concrete and observational.
- Distinguish clearly between what was actually retrieved from memory tools and what is an interpretation.
- Keep the "memory city" framing, but ground every claim in MCP results.
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.
- 1mo ago First seen · 43 lines · 37 tokens per session scan A cf403b157345
explore_memory_city is a command published in the GitHub repository jmeyer1980/neurodivergent-memory (24 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 556 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-12.
Other commands, from other repositories
setup
Install the agmem CLI and index the current repo for project memory.
remember
Save a fact to memini's long-term memory.
handoff
Save, list, or resume a memini session handoff for a fresh session.
pin
Pin a memini memory so it surfaces in every session briefing.
recall
Search memini for what you know about something.
backfill
Import past Claude Code sessions into memini as episodic memory.