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 skills add emaraschio/cursor-commands --skill update-memory-bankgit clone --depth 1 https://github.com/emaraschio/cursor-commandsWrote 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/skills/emaraschio/cursor-commands/update-memory-bank)<a href="https://agentmods.dev/skills/emaraschio/cursor-commands/update-memory-bank"><img src="https://agentmods.dev/badge/skills/emaraschio/cursor-commands/update-memory-bank/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/skills/emaraschio/cursor-commands/update-memory-bank"><img src="https://agentmods.dev/badge/skills/emaraschio/cursor-commands/update-memory-bank.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 | $0.00010 | $0.00461 |
| Opus 5.5 | $0.00004 | $0.00184 |
| Sonnet 5.5 | $0.00002 | $0.00092 |
| Haiku 4.5 | $0.00001 | $0.00046 |
Grade A, and why
update-memory-bank 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
Overview
Sync the memory bank with the current state of the repository and recent agent interactions. Run after significant work sessions, feature completions, or when context has drifted from reality.
Memory Bank Files
Each file has a distinct responsibility. Update only what changed:
| File | Purpose | Update when... |
|---|---|---|
activeContext.md |
Current state, recent commits, active work | After any meaningful commits |
progress.md |
Changelog, milestones, statistics | After feature completion |
techContext.md |
Tech stack, tools, environment | Tech stack changes |
systemPatterns.md |
Coding standards, patterns | New patterns established |
projectbrief.md |
Project purpose and scope | Rarely, only on major scope shifts |
Steps
-
Gather current state
- Run
git log --oneline -15to capture recent commits - Note any new files, commands, or rules added since last update
- Check
activeContext.md"Last Updated" date to understand the gap
- Run
-
Update each relevant file
activeContext.md: Update "Last Updated" date, "Latest Commits" list, "Recent Focus Areas", and "Cursor Commands Inventory" count if it changedprogress.md: Add a changelog entry for the current month if work occurred; update statistics if counts changed- Other files: Only touch if their specific domain changed
-
Verify accuracy
- Confirm commit hashes and descriptions match
git logoutput - Remove stale "Active Work Items" that are now complete
- Ensure statistics (command count, etc.) reflect reality
- Confirm commit hashes and descriptions match
-
Commit
- Use format:
docs(memory-bank): update memory bank with latest changes - Stage only memory bank files:
git add .cursor/memory-bank/ - Push to remote after commit
- Use format:
Guardrails
- Record only verified state; do not invent commits, files, or statistics.
- Update only the files whose domain changed; leave unchanged files alone.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 47 lines · 10 tokens per session scan A 089d2411d681
update-memory-bank is a skill published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 2d ago), licensed MIT. It adds 10 tokens to every session and 461 once invoked, about $0.0000 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 2026-09-03.
Other skills, from other repositories
audit-history
Use when reviewing past agent sessions, auditing memory health, identifying repeated corrections or friction, cleaning up stale memories, proposing new skills and rules from usage patterns, or identifying mechanical improvements (testing, linting, static analysis, tooling) that could improve outcomes.
docs-adr
Create and maintain lightweight Architecture Decision Records as agent-readable decision memory: what was decided, why, and what was rejected. Use when "record this decision", "set up ADRs", or "the agent keeps suggesting Y again".
docs-domain-modeling
Build a project's domain model: a CONTEXT.md glossary and ubiquitous language. Use when pinning down terminology, or the agent "uses the wrong words". Decision records (INDEX.md, rejected alternatives) → docs-adr.
minimax-m3-long-context
How to use MiniMax M3's 1M-token MSA context productively: what to load vs. compress, when to retrieve vs. ingest, how to keep skills shallow in the always-on prompt and deep in skills, and how to plan retention across iterations. Load when the task might exceed 200K tokens, when the user asks to "keep all of this in…
me-card
Render the user's saved /.me/ context as a single ASCII-art infographic card. Use when the user asks to "show my info", "print my card", "render my profile", "me card", "ascii infographic of my dot-me", or invokes the /me-card shortcut. Read-only — never writes to /.me/.
my-context-sync
A context-gathering process that collects information from several sources and combines it into one document.