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 agentmods add skills/vpeetla-ai/multi-agent-system-pattern/loop-engineeringnpx skills add vpeetla-ai/multi-agent-system-pattern --skill loop-engineeringgit clone --depth 1 https://github.com/vpeetla-ai/multi-agent-system-patternWhat 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 | $0.00048 | $0.00307 |
| Opus 5 | $0.00024 | $0.00153 |
| Sonnet 5 | $0.00010 | $0.00061 |
| Haiku 4.5 | $0.00005 | $0.00031 |
Grade A, and why
loop-engineering 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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- loop-engineering — 100% identical, 0 lines differ
What it actually says
Loop Engineering
ODAEU outer loop
| Phase | Action |
|---|---|
| Observe | Load RAG config vN, memory hints, corpus context |
| Decide | Plan ReAct steps or orchestrator decomposition |
| Act | MCP tools (read_file, search_docs) or repo patches |
| Evaluate | Recall, faithfulness, pytest, review score |
| Update | Tune RAG (top_k, hybrid_alpha) + write lesson |
RAG evolve signals
| Failure | Tune |
|---|---|
| low_recall | ↑ top_k, ↑ hybrid_alpha |
| low_faithfulness | ↑ rerank_threshold, ↓ hybrid_alpha |
Memory
Lesson(failure_mode, lesson, rag_version)→ JSON store (v1)- Hints injected on next run via
hints_for_query
MCP bridge
- Local adapters in
mcp/bridge.py; extensible to stdio MCP servers - Never give agents raw shell without allowlist
Reference
loop-engine-agent-platform/src/loop_engine/harness/loops/support-intelligence.yaml- ADR-001 in LoopForge repo
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.
- 2d ago First seen · 43 lines · 48 tokens per session scan A 7f855b529f66
loop-engineering is a skill published in the GitHub repository vpeetla-ai/multi-agent-system-pattern (2 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 307 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 2026-08-31.
Other skills, from other repositories
loop-engineering
Implement ODAEU harness loops, RAG evolve tuning, and procedural memory in LoopForge or similar systems. Use when building self-improving agents, eval gates, MCP tool bridges, or RAG version trees.
agent-builder
Build production-ready LLM agents with LangGraph, tool use, memory, streaming, and error handling. Use when designing or implementing an AI agent, multi-agent system, or agentic workflow.
langgraph-fundamentals
INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.
langgraph-human-in-the-loop
INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph. Covers interrupt(), Command(resume=...), approval/validation workflows, and the 4-tier error handling strategy.
dspy
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming.
jelou-build-workflows
The single entry point for building Jelou Brain workflows — one workflow or many. For a single-workflow intent ("construir un flujo", "armar un workflow", "build a workflow", "create a brain skill") this delegates straight to the build-workflow engine. For a multi-workflow intent it plans how the project decomposes…