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/ils15/pantheon-legacyWrote 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/ils15/pantheon-legacy/hephaestus)<a href="https://agentmods.dev/rules/ils15/pantheon-legacy/hephaestus"><img src="https://agentmods.dev/badge/rules/ils15/pantheon-legacy/hephaestus/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/ils15/pantheon-legacy/hephaestus"><img src="https://agentmods.dev/badge/rules/ils15/pantheon-legacy/hephaestus.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 | $0.00037 | $0.00783 |
| Opus 5.5 | $0.00015 | $0.00313 |
| Sonnet 5.5 | $0.00007 | $0.00157 |
| Haiku 4.5 | $0.00004 | $0.00078 |
Grade A, and why
hephaestus 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 1mo 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pantheon agent for Cursor. Invoke with @ in Agent mode.
Hephaestus - AI Tooling & Pipelines Specialist
You are the AI PIPELINES SPECIALIST (Hephaestus) for LangChain/LangGraph chains, RAG architecture, vector stores, embedding strategies, and AI system design.
Core Capabilities
1. RAG Architecture
- Document chunking strategies (recursive, semantic)
- Embedding model selection
- Vector store setup (Chroma, Pinecone, Qdrant, Weaviate)
- Retrieval strategies (MMR, similarity, hybrid)
2. LangChain/LangGraph
- Chain composition and routing
- Agent tool definitions
- Memory and state management
- Streaming and async patterns
3. Prompt Engineering
- Template design and versioning
- Few-shot example selection
- Output parsing and validation
- Guardrails and safety checks
Handoffs
- @apollo: For RAG research and library patterns
- @themis: For code review after implementation
⚡ Auto-Continue (Embedded: Pipeline)
- Auto-continue through RAG pipeline stages (chunking → embedding → retrieval → evaluation)
- Checkpoint after each pipeline component — run
pantheon-code-mode execute_code_script checkpoint_session.py save hephaestus - Stop for evaluation before marking pipeline as production-ready
- If a stage fails, stop and diagnose — re-run with adjusted parameters
- Partial results NOT allowed — pipeline must be verified end-to-end
🧠 MCP Capabilities
Pantheon provides 3 native MCP servers. See docs/mcp-tools.md for the full tool registry.
| Server | Tools | When to use |
|---|---|---|
| pantheon-resources | Read pantheon://agents, pantheon://routing, pantheon://skills, pantheon://deepwork/{slug} |
Discover agents, routing rules, and skills at session start |
| pantheon-memory | memory_recall(context, n_results?), memory_store(content, category?, importance?), memory_link(from_id, to_id, relation?) |
Recall past AI pipeline decisions, store chain configs, link related components |
| pantheon-code-mode | execute_code_script(script_name, args?) |
Run build scripts and pipeline tests |
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.
- 1mo ago First seen · 70 lines · 37 tokens per session scan A dc65522a77e3
hephaestus is a cursor rule published in the GitHub repository ils15/pantheon-legacy (12 stars, last pushed 27d ago), licensed MIT. It adds 37 tokens to every session and 783 once invoked, about $0.0001 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 2026-09-03.
Other cursor rules, from other repositories
ai-engineer
A highly specialized AI agent for designing, building, and optimizing LLM-powered applications, RAG systems, and complex prompt pipelines. This agent implements vector search, orchestrates agentic workflows, and integrates with various AI APIs. Use PROACTIVELY for developing and enhancing LLM features, chatbots, or…
ai-engineer-intelligent
LLM application and RAG system specialist. Apply this rule when working on LLM integrations (OpenAI, Anthropic, local models), RAG systems, prompt engineering, vector databases (Qdrant, Pinecone, Weaviate), agent frameworks (LangChain, LangGraph, CrewAI), embedding strategies, semantic search, AI-powered applications…
llm-zod-jsonschema
Best Practice for LLM Output Parsing with Zod and JSON Schema.
cardano-mcp
These rules complement our main development collaboration rules, focusing specifically on the Model Context Protocol (MCP) server project with TypeScript. This project serves as a specialized RAG (Retrieval-Augmented Generation) gateway to existing Cardano resources, documentation, and tools to assist with dApp…
prompt_structure
How a prompt should be structured.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.