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/adopt-memory-bank)<a href="https://agentmods.dev/rules/mehmetdemirci/comb-ai/adopt-memory-bank"><img src="https://agentmods.dev/badge/rules/mehmetdemirci/comb-ai/adopt-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/adopt-memory-bank"><img src="https://agentmods.dev/badge/rules/mehmetdemirci/comb-ai/adopt-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 | $0.00042 | $0.00662 |
| Opus 5.5 | $0.00017 | $0.00265 |
| Sonnet 5.5 | $0.00008 | $0.00132 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade A, and why
adopt-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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adopt Memory Bank — Cursor Rule (Brownfield Projects)
Trigger: User says "adopt memory bank", "add memory bank", or "setup memory bank for existing project". Unlike "create memory bank" (greenfield), this analyzes the existing codebase first.
When Triggered
Step 1 — Analyze the codebase first (don't ask)
Before asking questions, explore:
- Directory layout: Identify layers (backend, frontend, infra)
- Dependencies: Read package.json, *.csproj, go.mod, etc.
- Configuration: Config files, CI/CD pipelines
- Existing docs: README.md, architecture docs, ADRs
- Git history:
git log --oneline -20for recent focus - Tests: Test frameworks, coverage configuration
Step 2 — Present findings and confirm
Show the user what was discovered:
- Detected domains and tech stacks
- Architecture style (monolith, microservices, etc.)
- Recent development focus
- Existing documentation found
Ask: "Does this look correct? Anything to add or correct?"
Step 3 — Create pre-filled memory bank
Create the full structure with real data (not placeholders):
memory-bank/
├── INDEX.md ← From analysis
├── core/
│ ├── projectbrief.md ← From existing docs
│ ├── productContext.md ← From README or user input
│ ├── active-context.md ← From git log + user input
│ └── sprint-tracker.md ← Current sprint if applicable
├── tech/
│ └── [domain]-stack.md ← From dependency analysis
└── arch/
├── patterns-overview.md ← From code structure
└── decisions-summary.md ← From existing ADRs
Also create project root files:
memory-bank-protocol.md— COMB methodologyproject-rules.md— Pre-fill with detected conventions.cursor/rules/memory-bank.mdc— Auto-loader wrapper.cursor/rules/update-memory-bank.mdc— Auto-update rule
Step 4 — Report
Summarize what was created and flag inferences that need review.
Key Differences from Create (Greenfield)
| Greenfield | Brownfield |
|---|---|
| User answers questions | Codebase analysis first |
| Placeholders filled by user | Pre-filled from real data |
| Empty active context | Populated from git history |
| User describes architecture | Inferred from code |
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 · 79 lines · 42 tokens per session scan A cbd9864aecfc
adopt-memory-bank is a cursor rule published in the GitHub repository mehmetdemirci/comb-ai (13 stars, last pushed 8mo ago), licensed MIT. It adds 42 tokens to every session and 662 once invoked, about $0.0002 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
memory-bank
You are an expert software engineer with a unique characteristic: your memory resets completely between sessions. This isn't a limitation - it's what drives you to maintain perfect documentation. At the beginning of each dialogue, you rely ENTIRELY on your Memory Bank to understand the project and continue work…
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.