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/Sourcery-info/barracuda-mcpWrote 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/sourcery-info/barracuda-mcp/aleph-mcp-core)<a href="https://agentmods.dev/rules/sourcery-info/barracuda-mcp/aleph-mcp-core"><img src="https://agentmods.dev/badge/rules/sourcery-info/barracuda-mcp/aleph-mcp-core/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/sourcery-info/barracuda-mcp/aleph-mcp-core"><img src="https://agentmods.dev/badge/rules/sourcery-info/barracuda-mcp/aleph-mcp-core.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 | $0.00337 | $0.00337 |
| Opus 5 | $0.00169 | $0.00169 |
| Sonnet 5 | $0.00067 | $0.00067 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
aleph-mcp-core 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 8d 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
barracuda-mcp core rules
- Use the official
@modelcontextprotocol/sdkpatterns:McpServer,registerTool, and stdio transport for local Cursor use unless explicitly building a remote HTTP server. - Validate all tool inputs with Zod; keep schemas as the single source of truth and reuse them for
registerToolinputSchemawhere possible. - Never log API keys,
Authorizationheaders, or raw credential-bearing config. Redact errors that might echo secrets. - Keep HTTP access behind
AlephClient(or a small dedicated module). Injectfetch(orPick<AlephClient, "search">) in tests instead of calling production OpenAleph. - Map OpenAleph failures to MCP tool results with
isError: trueand a clear text message; include HTTP status and JSON body when safe. - OpenAleph auth for REST:
Authorization: ApiKey <key>and optionalX-Aleph-Session, matching the official Python client behavior. - Prefer small, pure helpers (URL building, env parsing) that are easy to unit test.
- Expose OpenAleph via tools:
aleph_search(/api/2/search),aleph_get_entity(/api/2/entities/:id), andaleph_get_entity_markdown(full Email Markdown or Pages plain text when structured output was truncated); keep structured response behavior documented inREADME.mdandprompts/.
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.
- 8d ago First seen · 16 lines · 337 tokens per session scan A 37ca84eec3c5
aleph-mcp-core is a cursor rule published in the GitHub repository Sourcery-info/barracuda-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 337 tokens to every session, about $0.0017 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 cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.