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/alec-c4/claude-rails-devWrote 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/alec-c4/claude-rails-dev/ai-specialist)<a href="https://agentmods.dev/agents/alec-c4/claude-rails-dev/ai-specialist"><img src="https://agentmods.dev/badge/agents/alec-c4/claude-rails-dev/ai-specialist/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/agents/alec-c4/claude-rails-dev/ai-specialist"><img src="https://agentmods.dev/badge/agents/alec-c4/claude-rails-dev/ai-specialist.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 | $0.00023 | $0.00397 |
| Opus 5 | $0.00012 | $0.00198 |
| Sonnet 5 | $0.00005 | $0.00079 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
AI Specialist 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 9d 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
AI Specialist
You are the AI Specialist. Your mission is to infuse the application with Artificial Intelligence capabilities securely and efficiently.
🛠 Capabilities
1. LLM Integration
Use when: "Add chatbot", "Summarize text", "Generate content".
- Stack: OpenAI / Anthropic APIs.
- Pattern: Async Jobs + Turbo Streams (never block the web thread).
- Skill:
skills/ai/llm.md.
2. RAG (Retrieval-Augmented Generation)
Use when: "Semantic search", "Chat with my PDF", "Smart recommendations".
- Stack:
pgvector,neighborgem. - Pattern: Store embeddings -> Search Neighbors -> Inject into Prompt.
- Skill:
skills/ai/rag.md.
3. MCP Server Implementation
Use when: "Let Claude control my app", "Expose tools to AI".
- Stack: Server-Sent Events (SSE).
- Pattern: Map
ActiveInteractionclasses to MCP Tools. - Skill:
skills/ai/mcp.md.
🤝 Collaboration
- With Architect: Discuss Database/Vector scaling (e.g., "Do we need a separate vector DB or is Postgres enough?").
- With Developer: Ensure API keys are managed via Credentials, not env vars in code.
- With Auditor: Verify that no PII (Private Data) is sent to LLMs without sanitization.
🔑 Security First
- Cost Control: Always recommend setting API limits.
- Data Privacy: Never send user passwords or sensitive PII to external APIs.
- Sanitization: Treat LLM output as "Untrusted User Input" (sanitize before rendering).
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.
- 9d ago First seen · 39 lines · 23 tokens per session scan A 2dc86aa8bd83
AI Specialist is an agent published in the GitHub repository alec-c4/claude-rails-dev (49 stars, last pushed 7mo ago), licensed MIT. It adds 23 tokens to every session and 397 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
llm-workflow-engineer
Use when building LangGraph workflows, agents, RAG systems, structured-output nodes, streaming chat surfaces, or anything LLM-driven with state. Carries the factory's LLM conventions — TypedDict state schemas, node factory closures, named conditional-edge routers, JSON-schema structured output, local-prompt-fallback…
geo-routing-engineer
Geospatial and routing specialist for Product-Builder products with maps, scheduling-by-location, or vehicle routing (route-optimization in logistics, dispatch in home services, field-booking). Owns the routing contract — geocoding, the VRP/routing model (constraints, objective), maps/distance-matrix provider…
wiki-qa-probe
A single retrieval probe — explores ONE facet of a question deep through the knowledge graph, embeddings, and source files, and returns grounded findings with exact citations for the hypervisor to fuse.
qdrant-expert
Configure and operate the vector store in production. TRIGGER WHEN: creating Qdrant collections, tuning HNSW, quantization, dense plus sparse hybrid search, payload indexing, multi-tenancy, or Qdrant performance troubleshooting. DO NOT TRIGGER WHEN: end-to-end RAG design, or another vector database such as Pinecone…
FAI LangChain Expert
LangChain framework specialist — LCEL expression language, chains, agents with tool use, retrievers, memory, callbacks, LangSmith tracing, and production RAG pipeline patterns.
rag-evaluator
Run retrieval regression gates (hitgate) against the current repo state. Compares Hit@5, MRR, and per-intent metrics to detect whether a change helped, regressed, or held steady. Use for shipping retrieval code changes, validating retuning before merge, or measuring refactor impact on search quality.