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/0xfurai/claude-code-subagentsWrote 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/agents/0xfurai/claude-code-subagents/bullmq-expert)<a href="https://agentmods.dev/agents/0xfurai/claude-code-subagents/bullmq-expert"><img src="https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/bullmq-expert.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 | $0.00029 | $0.00440 |
| Opus 5 | $0.00015 | $0.00220 |
| Sonnet 5 | $0.00006 | $0.00088 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
bullmq-expert 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Focus Areas
- Efficient job processing and queue management with BullMQ
- Advanced job scheduling and delayed jobs
- Job prioritization and concurrency control
- Queue event handling and monitoring
- Error handling and retry strategies for failed jobs
- Graceful shutdown and job continuity
- Job data persistence and state management
- Rate limiting and job throttling
- Integration with Redis for optimized performance
- Performant real-time job processing at scale
Approach
- Utilize repeatable job patterns for routine tasks
- Implement robust backoff and retry strategies
- Separate concerns with worker, queue, and event listeners
- Use named job queues for logical separation
- Optimize job concurrency settings based on workload
- Monitor queue health and worker status regularly
- Set up alerts for failed and stalled jobs
- Use BullMQ Events API for effective event-driven architecture
- Document queue processes and configurations thoroughly
- Test job flows with real-world data scenarios
Quality Checklist
- All jobs have unique, traceable IDs
- Job payloads are validated before processing
- Comprehensive tests cover all job scenarios
- Queue configurations are documented and version controlled
- Error and delay thresholds are clearly defined
- Jobs are stateless and do not rely on in-memory state
- High-availability Redis setup to minimize downtime
- Priority queues are used where necessary
- Metrics and logging integrated with APM tools
- Alerting configured for job failure and latency spikes
Output
- Well-structured BullMQ-based job processing system
- High availability and fault-tolerant task queues
- Configurable job retries and backoff strategies
- Detailed metrics and logs for queue performance
- Automated system alerts for job failures
- Documentation for setup, usage, and maintenance
- Scalable infrastructure for handling increased load
- Codebase adhering to established BullMQ best practices
- Efficient job consistency and state management
- Reliable integration with Redis ensuring data durability
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 · 59 lines · 29 tokens per session scan A 34621bd415cb
bullmq-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (996 stars, last pushed 10mo ago), licensed MIT. It adds 29 tokens to every session and 440 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 2026-08-30.
Other agents, from other repositories
redis-expert
Redis data structures, caching strategies, pub/sub, Lua scripting, cluster topology, and eviction policies specialist.
backend-architect
Expert in backend system design, microservices architecture, event-driven patterns, caching strategies, database selection, and scalability patterns. Use when designing distributed systems, evaluating architectural trade-offs, or establishing back...
redis
Caching, session management, pub/sub, rate limiting, and streams with Redis.
backend-engineer
Builds the backend for Sprint Zero — an Express, FastAPI, or Next.js API, or a CLI program — against the build configuration in docs/scope.md and the contract in docs/api-contract.md. Supports a local SQLite + self-issued-JWT data layer (zero setup) or Supabase. Invoked by the main Claude Code session during the build…
backend-platform-engineer
Implementation specialist for backend services. Use PROACTIVELY when the task involves NestJS, Node.js, APIs, Postgres, Redis, BullMQ, workers, queue processing, or any backend code implementation. Handles implementation after principal-engineer designs.
backend-dev
An agent for building and fixing server-side software, including APIs, business rules, databases, background jobs, authentication, and caching.