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/usewire/wire-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/rules/usewire/wire-memory/wire-memory-search)<a href="https://agentmods.dev/rules/usewire/wire-memory/wire-memory-search"><img src="https://agentmods.dev/badge/rules/usewire/wire-memory/wire-memory-search/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/usewire/wire-memory/wire-memory-search"><img src="https://agentmods.dev/badge/rules/usewire/wire-memory/wire-memory-search.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 | $0.00310 | $0.00310 |
| Opus 5.5 | $0.00124 | $0.00124 |
| Sonnet 5.5 | $0.00062 | $0.00062 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
wire-memory-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 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
Wire Memory — Search
Check ~/.wire-memory/context.md for connection status. If the file exists and shows "Connected", Wire memory is active. Use the User and Project values from that file as your scoping parameters.
When to Search
- Session start — recent session summaries for this project
- Before suggesting an approach — past corrections or decisions that apply
- When user references past work — what was discussed or decided
Three retrieval surfaces, pick by what you're looking for:
wire_explore— structured access to indexed entities (decisions, corrections, patterns, preferences). Modes:schema,list,get,filter,text. Start withmode: "text"for keyword match across all entities, ormode: "filter"with aprojectpredicate.wire_search— natural-language semantic match over notes, uploaded files, and recent writes that haven't been turned into indexed entities yet. Pass a specificquery. There is nomodeparameter.wire_navigate— from awire_searchmatch's id, reach itssiblings, fullsource, orrelationships.
Scope: filter by project name first. Broaden only if no results.
Run wire_explore (no params) once on a new container to see what's stored before your first search.
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 · 25 lines · 310 tokens per session scan A 929622a65c6d
wire-memory-search is a cursor rule published in the GitHub repository usewire/wire-memory (10 stars, last pushed 5mo ago), licensed MIT. It adds 310 tokens to every session, about $0.0012 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
cursor-rules
You have access to a persistent cross-session memory via the memory MCP server. Knowledge survives between sessions and is shared across agents working on the same project.
atomicmemory
AtomicMemory persistent memory protocol and MCP tool usage.
memento-workflows
Memento OS — session lifecycle and decision workflows.
memento-conventions
Memento OS — reasoning artifact conventions for persistent AI memory.
context-bank
Global project rules and context source of truth.
CURSOR.rules
A set of Cursor rules that acts as the entry point for Baton, a project handoff system for keeping work, memory, and Git history consistent across AI coding tools.