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/mehmetdemirci/comb-aiWrote 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/mehmetdemirci/comb-ai/update-memory-bank)<a href="https://agentmods.dev/rules/mehmetdemirci/comb-ai/update-memory-bank"><img src="https://agentmods.dev/badge/rules/mehmetdemirci/comb-ai/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/rules/mehmetdemirci/comb-ai/update-memory-bank"><img src="https://agentmods.dev/badge/rules/mehmetdemirci/comb-ai/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 | $0.00701 | $0.00701 |
| Opus 5.5 | $0.00280 | $0.00280 |
| Sonnet 5.5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
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 2mo 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Bank Auto-Update — Cursor Rule
Always active. This rule ensures the AI automatically updates the memory bank when task completion is detected. No manual trigger required.
Manual override: User says "update memory bank" for a full-scope review.
Automatic Trigger Conditions
AI MUST detect task completion and automatically execute memory bank update when:
- Task implementation completed (code changes committed or ready)
- Sprint task marked complete
- Bug fix implemented
- Feature implementation finished
- Architectural decision made
Completion Signal Detection
AI MUST monitor for these signals to trigger auto-update:
- User says: "done", "finished", "complete", "task completed"
- After implementing and testing code changes
- After fixing bugs
- After architectural decisions documented
- At end of sprint milestone
- When user asks "What's next?" or "Next task?"
Scope Detection
Determine scope automatically based on what changed:
- Minimal: Single task completed → sprint-tracker + active-context
- Standard: Feature implemented → + progress
- Full: Sprint completed or major milestone → + archive + arch/tech files
- Architecture: Architecture decision made → + arch/patterns-overview + decisions-summary
- Tech Stack: New dependency or technology → + relevant tech/*.md
Update Priority Order
- core/sprint-tracker.md → Task status, actual hours, completion percentage
- core/active-context.md → Current work, next steps, resolved blockers
- core/progress.md → What works, what's left, overall status (standard/full only)
- project-rules.md dynamic zone → Recent patterns catalog, sprint context
- tech/*.md → If tech stack changed
- arch/*.md → If architecture changed
Report Format
After updating, report concisely:
Memory Bank Updated
Scope: [minimal/standard/full/architecture/tech-stack]
Trigger: [task description]
Updated:
- core/sprint-tracker.md → [what changed]
- core/active-context.md → [what changed]
Next steps:
- [what's next]
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.
- 2mo ago First seen · 98 lines · 701 tokens per session scan A 6c757c8b3113
update-memory-bank is a cursor rule published in the GitHub repository mehmetdemirci/comb-ai (13 stars, last pushed 8mo ago), licensed MIT. It adds 701 tokens to every session, about $0.0028 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 2026-08-30.
Other cursor rules, from other repositories
component-development
Modern React + TypeScript component patterns — hooks, typed props, performance optimization, forms, and testing.
webdriver-management
Selenium WebDriver lifecycle management — driver factory, explicit waits, browser options, and teardown.
api-testing
Cypress network interception and API testing patterns (cy.intercept, service mocking, request/response validation).
app-router-patterns
Next.js 14+ App Router patterns — Server Components, Client Components, Route Handlers, Server Actions, and metadata API.
test-patterns
Selenium pytest test patterns — data-driven tests, fixtures, error handling, and performance checks.
page-object-patterns
Page Object Model patterns for Selenium — BasePage, component objects, and fluent interfaces.