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/jaycewalzer1/SilverKey-Inc.Wrote 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/jaycewalzer1/silverkey-inc./agent-memory)<a href="https://agentmods.dev/rules/jaycewalzer1/silverkey-inc./agent-memory"><img src="https://agentmods.dev/badge/rules/jaycewalzer1/silverkey-inc./agent-memory/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/jaycewalzer1/silverkey-inc./agent-memory"><img src="https://agentmods.dev/badge/rules/jaycewalzer1/silverkey-inc./agent-memory.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 | $0.00000 | $0.00608 |
| Opus 5.5 | $0.00000 | $0.00243 |
| Sonnet 5.5 | $0.00000 | $0.00122 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
agent-memory 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent memory (SilverKey)
Layers (use the right one)
| Layer | Where | Use for |
|---|---|---|
| Repo memory bank | .cursor/memory/*.md (this rule) |
Team-visible session focus, progress, stable project notes |
| Project rules | .cursor/rules/*.mdc |
Enforced always/never patterns |
| AGENTS.md + company rules | Repo root + .cursor/rules/shared/* |
Quickstart, company context, RESPA |
| Cursor Settings → Memories | Cursor app (account) | Personal preferences across projects |
| Automations → Memories → Manage | Cursor cloud per automation | Memory-tool files for scheduled agents |
MCP cursor-memory |
.cursor/mcp.json |
Optional /memo, /recall (local SQLite) |
Do not duplicate long prose from AGENTS.md or rules into memory files — link or one-line point.
When to read .cursor/memory/
Before continuing the same workstream (or when explicitly asked for memory context), read:
projectbrief.md— scope and compliance reflextechContext.md— commands and version pinsactiveContext.md— what we are doing nowprogress.md— recent shipped work
When to update
After completing a feature, significant refactor, or architecture change:
- Update
activeContext.md(current focus / open questions). - Append a dated entry to
progress.md(what shipped, gates run, follow-ups). - If stack or conventions changed, update
techContext.md. - For cross-cutting doc/rule changes, follow
documentation/internal/post-major-change-checklist.md.
MCP memory (if enabled)
When cursor-memory MCP is enabled in Cursor Settings → MCP:
- Use
/recall(or tool search) before re-deriving prior decisions. - Use
/memowhen the user asks to remember something ad hoc (not already in rules).
Automations
Cursor Automations store memory on Cursor’s servers (not git). Optimized seeds live in .cursor/memory/automations/:
_core.md— prepend to every automation memory file<persona>.md— match automation purpose (seeautomations/README.md)- Print for paste:
./scripts/print-automation-memory.sh <persona>from repo root
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 · 58 lines · 0 tokens per session scan A 201b328bba17
agent-memory is a cursor rule published in the GitHub repository jaycewalzer1/SilverKey-Inc. (2 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 608 tokens. 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
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
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.