Trader Cloud Backtest

What it does

When your agent uses it

• Tasks that involve Trading and backtesting
• Tasks that involve Fine-tuning

Example prompts

• “/trader-cloud-backtest”

Requirements

• Node.js
• A credential in ANTHROPIC_API_KEY
• A credential in CLAUDE_API_KEY
• Pre-approved tools (allowed-tools): mcp__plugin_ruflo-core_ruflo__managed_agent_create, mcp__plugin_ruflo-core_ruflo__managed_agent_prompt, mcp__plugin_ruflo-core_ruflo__managed_agent_events, mcp__plugin_ruflo-core_ruflo__managed_agent_status, mcp__plugin_ruflo-core_ruflo__managed_agent_terminate, mcp__plugin_ruflo-core_ruflo__memory_store, mcp__plugin_ruflo-core_ruflo__memory_retrieve, mcp__plugin_ruflo-core_ruflo__memory_search, mcp__plugin_ruflo-core_ruflo__agentdb_pattern-store, Bash, Read

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Estimate first. From the job size, print an estimated cost (≈ container-minutes × rate + tokens) — a long sweep is a deliberate choice…
2. 2Provision (or reuse) the container — install neural-trader at container start so the agent doesn't reinstall mid-run
3. 3Pre-flight cheap. Before a 1000-path / multi-year run, do a tiny smoke first (1 MC path, ~3 months) — catches a bad strategy name / symbol…
4. 4Run the real job
5. 5Pull artifacts (if needed): managed_agent_prompt({ sessionId, message: "cat /tmp/equity.csv" }) or managed_agent_events and read the…
6. 6Ingest locally + Ed25519 verify (ADR-126 Phase 4 fail-closed gate)
7. 7Terminate immediately — results in hand

What it can do on your machine

Read from SKILL.md and the folder at commit de590e1. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • mcp__plugin_ruflo-core_ruflo__managed_agent_create
  • mcp__plugin_ruflo-core_ruflo__managed_agent_prompt
  • mcp__plugin_ruflo-core_ruflo__managed_agent_events
  • mcp__plugin_ruflo-core_ruflo__managed_agent_status
  • mcp__plugin_ruflo-core_ruflo__managed_agent_terminate
  • mcp__plugin_ruflo-core_ruflo__memory_store
  • mcp__plugin_ruflo-core_ruflo__memory_retrieve
  • mcp__plugin_ruflo-core_ruflo__memory_search
  • mcp__plugin_ruflo-core_ruflo__agentdb_pattern-store
  • Bash

  …and 1 more on the same allowed-tools line.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • npx

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • ANTHROPIC_API_KEY
  • CLAUDE_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Trader Cloud Backtest loads about 1.8k tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 444 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~46

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: mcp__plugin_ruflo-core_ruflo__managed_agent_create, mcp__plugin_ruflo-core_ruflo__managed_agent_prom

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ruvnet/ruflo at commit de590e1, republished under its MIT licence (© ruvnet). 444 words, ~1,808 tokens.

name

trader-cloud-backtest

description

Run a heavy neural-trader job (long walk-forward, big Monte-Carlo, parameter sweep, model training) on the Anthropic Managed Agent cloud runtime instead of locally

allowed-tools

mcp__plugin_ruflo-core_ruflo__managed_agent_create, mcp__plugin_ruflo-core_ruflo__managed_agent_prompt, mcp__plugin_ruflo-core_ruflo__managed_agent_events, mcp__plugin_ruflo-core_ruflo__managed_agent_status, mcp__plugin_ruflo-core_ruflo__managed_agent_terminate, mcp__plugin_ruflo-core_ruflo__memory_store, mcp__plugin_ruflo-core_ruflo__memory_retrieve, mcp__plugin_ruflo-core_ruflo__memory_search, mcp__plugin_ruflo-core_ruflo__agentdb_pattern-store, Bash, Read

argument-hint

<backtest|train|sweep> <strategy-or-model> --symbol <TICKER> [--period 2020-2024] [--mc-paths 1000]

managed_agent_create  { "name":"nt-cloud", "model":"claude-haiku-4-5-20251001", "packages":{"npm":["neural-trader"]}, "initScript":"npm install -g --ignore-scripts neural-trader >/dev/null 2>&1 || true" }
  → { sessionId:"sesn_…", environmentId:"env_…" }
managed_agent_prompt   { "sessionId":"sesn_…", "message":"Run `npx neural-trader --backtest --strategy multi-indicator --symbol SPY --period 2020-2024 --walk-forward --mc-paths 1000`. Report Sharpe/Sortino/max-DD/win-rate/CVaR; write /tmp/equity.csv. Then stop.", "maxWaitMs":600000 }
  → { finished:true, status:"idle", assistantText:"<metrics>", toolUses:[{bash:"npx neural-trader --backtest …"}] }
# … memory_store the metrics, agentdb_pattern-store if Sharpe>1.5, record cost …
managed_agent_terminate { "sessionId":"sesn_…", "environmentId":"env_…" }

© ruvnet, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/ruflo-neural-trader/skills/trader-cloud-backtest of ruvnet/ruflo.

Open the folder on GitHubat commit de590e1