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.
npx agentmods add rules/usewire/wire-memory/wire-memory-writegit clone --depth 1 https://github.com/usewire/wire-memoryWhat 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 | $0.00246 | $0.00246 |
| Opus 5 | $0.00123 | $0.00123 |
| Sonnet 5 | $0.00049 | $0.00049 |
| Haiku 4.5 | $0.00025 | $0.00025 |
Grade A, and why
wire-memory-write 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 yesterday.
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 — Write
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 in all writes.
When to Write
Log silently as moments happen — don't announce it:
- Decision made — user picks an approach or you evaluate trade-offs
- Correction received — user corrects your approach (highest value)
- Pattern established — a convention is set or repeated
- Session ending — brief summary of what was done and what's next
Use wire_write via MCP with structured JSON. Always include type, project, user, scope.
Scope: "project" for project-specific context (default), "global" for cross-project preferences.
Before Writing
Search first for existing entries on the same topic. If outdated, delete with wire_delete then write the replacement.
Do NOT Log
Secrets, credentials, PII, stack traces, verbatim code, or things already in git history.
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.
- yesterday First seen · 30 lines · 246 tokens per session scan A 4aa8221cf5c9
wire-memory-write is a cursor rule published in the GitHub repository usewire/wire-memory (10 stars, last pushed 3mo ago), licensed MIT. It adds 246 tokens to every session, about $0.0012 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.
Other cursor rules, from other repositories
atomicmemory
AtomicMemory persistent memory protocol and MCP tool usage.
CURSOR.rules
Baton 项目协作入口。口令（上班啦/下班啦等）必须按 Baton skill 执行。.
openai-agents-overview
Comprehensive reference for building with the OpenAI Agent SDK.
langgraph-best-practices
Comprehensive reference for building LangGraph agent workflows including core concepts, graph construction patterns, state management, advanced patterns like Send API and Command, and production-ready code examples.
03-skill-testcases
SKILL: Generate Test Scenarios Matrix from API spec (use for /api-isolated-tests).
01-qa-agent
QA AGENT PERSONA: Principles, Anti-patterns, workflows.