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 seed-forge/harness-ai-kit --skill public-rabbitmq-expert-basegit clone --depth 1 https://github.com/seed-forge/harness-ai-kitWrote 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/seed-forge/harness-ai-kit/public-rabbitmq-expert-base)<a href="https://agentmods.dev/skills/seed-forge/harness-ai-kit/public-rabbitmq-expert-base"><img src="https://agentmods.dev/badge/skills/seed-forge/harness-ai-kit/public-rabbitmq-expert-base/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/seed-forge/harness-ai-kit/public-rabbitmq-expert-base"><img src="https://agentmods.dev/badge/skills/seed-forge/harness-ai-kit/public-rabbitmq-expert-base.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 | $0.00048 | $0.00659 |
| Opus 5 | $0.00024 | $0.00329 |
| Sonnet 5 | $0.00010 | $0.00132 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
public-rabbitmq-expert-base 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 11d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RabbitMQ Knowledge Base
Source: Adapted from mindrally/skills (rabbitmq-development) and RabbitMQ official documentation.
Exchange Types
| Type | Routing | Use for |
|---|---|---|
| Direct | Exact routing key match | Point-to-point, RPC |
| Topic | Wildcard pattern (*.info, #) |
Flexible pub/sub |
| Fanout | Ignore routing key, broadcast to all bound queues | Broadcast notifications |
| Headers | Match on message headers (not routing key) | Complex routing rules |
- Default exchange (empty name): direct routing by queue name. Convenient but not recommended for production.
- Always declare exchanges explicitly; don't rely on auto-created exchanges.
Queue & Routing
- Declare queues with
durable=truefor persistence across broker restarts. - Bind queues to exchanges with routing keys.
- Use
x-message-ttlfor message expiration. - Use
x-max-lengthto cap queue size (drop or dead-letter oldest). - Prefetch count (
basic_qos): limit unacknowledged messages per consumer.
Durability & Reliability
durable=trueon queue +persistentdelivery mode on message = survive broker restart.- Publisher confirms:
confirm_select()→ broker acknowledges message receipt. - Consumer acknowledgments:
basic_ack(success) /basic_nack(failure, requeue or dead-letter). - Never use
auto_ack=truein production (message loss on consumer crash).
Dead Letter Exchange (DLX)
- Messages are dead-lettered when: rejected (
basic_nackwith requeue=false), TTL expired, or queue length exceeded. - Configure with
x-dead-letter-exchangeandx-dead-letter-routing-keyon the source queue. - Use DLX for retry queues, error handling, and audit trails.
- Pattern: main queue → DLX → retry queue (with TTL) → main queue.
Connection & Channel
- One connection per application; multiple channels per connection.
- Channels are lightweight; connections are expensive (TCP + AMQP handshake).
- Use connection pooling for multi-threaded applications.
- Set
heartbeatinterval (default 60s) to detect dead connections.
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.
- 11d ago First seen · 58 lines · 48 tokens per session scan A 4f680b4caecc
public-rabbitmq-expert-base is a skill published in the GitHub repository seed-forge/harness-ai-kit (22 stars, last pushed 10d ago), licensed Apache-2.0. It adds 48 tokens to every session and 659 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
api-tester
Test and document API endpoints - validate responses, check status, generate examples.
helius
Skill "helius" from helius-labs/core-ai, covering helius — build on solana, prerequisites, 1. helius mcp server, 2. mcp router surface and 3. api key.
REST API Endpoint Designer
Designs RESTful API endpoints following OpenAPI spec and industry best practices.
Caching Strategy Advisor
Recommends the right caching layer, TTL strategy, and invalidation approach for any application bottleneck.
MCP Integration Assistant
Helps design and implement Model Context Protocol (MCP) server integrations for AI agents.
API Documentation Generator
Generates OpenAPI-compatible documentation for REST API endpoints from code or route definitions.