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.
git clone --depth 1 https://github.com/lezards/neuron-vault-kitWrote 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/rules/lezards/neuron-vault-kit/neuron-vault-read)<a href="https://agentmods.dev/rules/lezards/neuron-vault-kit/neuron-vault-read"><img src="https://agentmods.dev/badge/rules/lezards/neuron-vault-kit/neuron-vault-read/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/rules/lezards/neuron-vault-kit/neuron-vault-read"><img src="https://agentmods.dev/badge/rules/lezards/neuron-vault-kit/neuron-vault-read.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 | $0.00363 | $0.00363 |
| Opus 5.5 | $0.00145 | $0.00145 |
| Sonnet 5.5 | $0.00073 | $0.00073 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
neuron-vault-read 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
NeuronVault — leitura
Este projeto usa NeuronVault, um sistema de memória persistente baseado em arquivos .md.
Antes de responder ao usuário
- Sempre leia
neuron-vault/MEMORY.md— é o índice de memórias. - Se uma entrada do índice é relevante ao tópico atual, leia o neuron completo em
neuron-vault/neurons/<arquivo>.md. - Se houver daily notes recentes em
neuron-vault/daily/(últimos 2-3 dias), leia para contexto temporal.
Tipos de memória
| Tipo | Conteúdo |
|---|---|
user |
Quem é o usuário, role, stack, preferências |
feedback |
Correções/aprovações que ele deu — siga essas regras |
project |
Estado de iniciativas, decisões, deadlines |
reference |
Onde achar info em sistemas externos |
skill |
Procedimentos repetitivos que o usuário documentou |
Comportamento esperado
- Aplique
feedbackautomaticamente sem repetir guidance que o usuário já deu. - Use
userprofile pra calibrar profundidade técnica e tom. - Cite
referencequando relevante ("vê o ticket no Linear INGEST"). - Trate
projectcomo contexto vivo — fatos podem ter mudado, verifique no código quando crítico.
Quando memória conflita com código atual
Memórias podem ficar obsoletas. Se um neuron diz "função X faz Y" mas você lê o código e Y mudou, confie no código e atualize/remova o neuron stale.
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 · 36 lines · 363 tokens per session scan A 3e99e66f5b08
neuron-vault-read is a cursor rule published in the GitHub repository lezards/neuron-vault-kit (2 stars, last pushed 2mo ago), licensed MIT. It adds 363 tokens to every session, about $0.0015 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 2026-08-31.
Other cursor rules, from other repositories
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
dreamd-recall
Search dreamd at the start of a task and quote a hit. Append when the user corrects you or states a decision.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
common_memory_bank
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
self-improving-obsidian-llm-wiki
LLM Wiki OS operating rules.
memsprout
Cursor rule "memsprout" from memsprout/agents, covering using memsprout, search first, capturing, spaces and topics and files.