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/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/commands/emaraschio/cursor-commands/update-memory-bank)<a href="https://agentmods.dev/commands/emaraschio/cursor-commands/update-memory-bank"><img src="https://agentmods.dev/badge/commands/emaraschio/cursor-commands/update-memory-bank.svg" alt="Measured on agentmods" 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 | $0.00359 |
| Opus 5 | $0.00005 | $0.00179 |
| Sonnet 5 | $0.00002 | $0.00072 |
| Haiku 4.5 | $0.00001 | $0.00036 |
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 7d 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 memory bank with repository state. Full workflow: .cursor/skill-contracts/update-memory-bank/SKILL.md (user install: ~/.cursor/skill-contracts/update-memory-bank/SKILL.md).
Defaults
None. See skill for workflow defaults.
Steps
- Read
.cursor/skill-contracts/update-memory-bank/SKILL.mdfor the full agent contract; if that file is missing, read~/.cursor/skill-contracts/update-memory-bank/SKILL.md. - Execute the workflow in order; do not skip safety steps.
- Report outcomes per skill (summary, tables, or checklist as specified).
Anti-patterns
- Record only verified state. Trigger: writing memory bank entries. Wrong: inventing commits, files, or statistics. Correct: confirm commit hashes and descriptions against git log before recording them. Reason: fabricated history makes the memory bank untrustworthy.
- Update only what changed. Trigger: choosing which memory bank files to edit. Wrong: rewriting files whose domain did not change. Correct: update only the files whose domain actually changed. Reason: needless edits create churn and hide real updates.
Examples
/update-memory-bank
Maintainers
Behavioral eval: .cursor/skill-contracts/update-memory-bank/eval/cases.md. Ship gate sections: A before changing SKILL.md or this command.
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.
- 7d ago First seen · 38 lines · 10 tokens per session scan A a21015e845bd
update-memory-bank is a command published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 359 once invoked, about $0.0001 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 commands, from other repositories
init-workspace-flow
Workflow for initializing or upgrading a workspace: context, discovery, documentation, etc.
init-workspace-flow-discovery
Phase 3 Discovery of init-workspace-flow.
consolidate
Dream cycle -- promote patterns, prune stale, reconcile contradictions, optionally promote to global.
memory-audit
List auto-extracted memory entries for review. Remove any with /ijfw memory forget .
memory-why
Show why a memory recall returned what it did -- BM25 vs vector vs hybrid provenance.
init-workspace-flow-codegraph
Phase 6 Code-graph of init-workspace-flow.