agentmods.dev

diepi-quant-research

diepi-quant-research is a skill for Claude Code, Codex from elonmaskhair-prog/dsh-plugin-diepi. It costs 59 tokens per session (1,520 once invoked), scanned A, original, Apache-2.0.

A workflow for turning a natural-language daily stock or exchange-traded fund idea into a typed strategy and testing it on historical data. An exchange-traded fund is a market-traded basket of investments.

In plain words
What is it for?
Defining and backtesting supported daily, long-only moving-average crossover strategies, optionally using an amount-expansion entry filter and verified Tushare data.
Why use it?
It makes backtests repeatable and auditable while limiting unsupported requests, such as live trading, short selling, leverage, or intraday strategies.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 1repo 1mo ago A scan 59 tokens original Apache-2.0

Good fit Defining and backtesting supported daily, long-only moving-average crossover strategies, optionally using an amount-expansion entry filter and verified Tushare data.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/elonmaskhair-prog/dsh-plugin-diepi/diepi-quant-research
View source ↗ elonmaskhair-prog/dsh-plugin-diepi
Install

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.

Any agent
npx skills add elonmaskhair-prog/dsh-plugin-diepi --skill diepi-quant-research
Clone the repo
git clone --depth 1 https://github.com/elonmaskhair-prog/dsh-plugin-diepi

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for diepi-quant-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/elonmaskhair-prog/dsh-plugin-diepi/diepi-quant-research/github.svg)](https://agentmods.dev/skills/elonmaskhair-prog/dsh-plugin-diepi/diepi-quant-research)
Your own site
<a href="https://agentmods.dev/skills/elonmaskhair-prog/dsh-plugin-diepi/diepi-quant-research"><img src="https://agentmods.dev/badge/skills/elonmaskhair-prog/dsh-plugin-diepi/diepi-quant-research/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.

agentmods 80×15 button for diepi-quant-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/elonmaskhair-prog/dsh-plugin-diepi/diepi-quant-research"><img src="https://agentmods.dev/badge/skills/elonmaskhair-prog/dsh-plugin-diepi/diepi-quant-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,520 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.01520
Opus 5.5 $0.00024 $0.00608
Sonnet 5.5 $0.00012 $0.00304
Haiku 4.5 $0.00006 $0.00152

Measured 2mo ago against content hash b686c7ded20a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

diepi-quant-research 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 2mo 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.

dsh/skills/diepi-quant-research/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

diePi quantitative research

Use this workflow when the user wants to express a stock or ETF strategy in natural language and backtest it with diePi.

Hard boundary

  • This integration is for research and backtesting only. It has no live-order tool.
  • Never pass or execute arbitrary Python through diePi tools. Any optional external Skill runs separately under the host's own tool and permission policy.
  • StrategySpec v1 currently supports one daily, long-only ma_crossover strategy with an optional amount-expansion entry filter.
  • Do not claim support for futures, leverage, short selling, intraday or minute data, portfolio optimization, or a built-in data connector.
  • Treat Tushare acquisition as an optional handoff to the independently installed official Tushare Skill. Never request, receive, echo, or log a Tushare token in chat or in diePi tool arguments.

Workflow

  1. Call mcp__diepi__capabilities and select an opaque dataset_id. Read its data_contract and execution_model; these are part of the strategy interpretation, not optional boilerplate. If no configured dataset can cover the requested daily instrument and interval, do not invent an ID: read the Tushare handoff and follow its missing-data branch.
  2. Translate the user's words into StrategySpec v1. Do not invent a ticker, date interval, or economically material trading assumption. Ask if one is missing.
  3. Call mcp__diepi__preview_strategy. Show the strategy card when its exact entry, exit, position, or information boundary could surprise the user.
  4. Call mcp__diepi__validate_data for the exact symbol, interval, and price mode. If the configured data is ready, skip all acquisition. If required daily data is missing, read the Tushare handoff and follow it. Validate the staged and host-registered market_data_v1 dataset again. Treat validation as a hard gate: never start a backtest after a failed or incomplete validation. A warning is evidence to disclose, not text to silently discard.
  5. Generate and record one stable submission_id for this exact execution request. Use req_ followed by 8 to 64 ASCII letters, digits, _, or -; a fresh 32-character hexadecimal nonce is a good suffix. Never reuse the ID for different dataset, strategy, backtest, or execution-assumption values.
  6. Call mcp__diepi__start_backtest with that submission_id. It validates again and returns quickly with a job_id; it never waits for the whole run. If the call times out or its transport fails, retry the exact same arguments with the same submission_id. Never generate a replacement ID for a retry.
  7. Poll mcp__diepi__job_status at a reasonable cadence. Use mcp__diepi__cancel_job when the user asks to stop.
  8. Call mcp__diepi__get_result. Treat a run as comparable only when all are true: artifact_verified == true, adapter_attribution_verified == true, result_committed == true, result_status == SUCCESS, and rankable == true.

Read the full file on GitHub · 119 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 2mo ago First seen · 119 lines · 59 tokens per session scan A b686c7ded20a

Subscribe to this mod's changes

diepi-quant-research is a skill published in the GitHub repository elonmaskhair-prog/dsh-plugin-diepi (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,520 once invoked, about $0.0002 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 2026-08-31.

Analytics and metricsFinance and fintechbacktestingdiepidsh-pluginmcpquantitative-finance
Related

diepi-quant-research compared with skills from other repositories

diepi-quant-research next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
diepi-quant-researchelonmaskhair-prog/dsh-plugin-diepiSkill11mo agoApache-2.0A59Claude Code, Codex
tushareHKUDS/Vibe-TradingSkill38ktodayMITA79Claude Code, Codex
correlation-analysisHKUDS/Vibe-TradingSkill38ktodayMITA57Claude Code, Codex
social-media-intelligenceHKUDS/Vibe-TradingSkill38ktodayMITA28Claude Code, Codex
vibe-tradingHKUDS/Vibe-TradingSkill38ktodayMITA172Claude Code, Codex
ashare-pre-st-filterHKUDS/Vibe-TradingSkill38ktodayMITA89Claude Code, Codex
credit-analysisHKUDS/Vibe-TradingSkill38ktodayMITA36Claude Code, Codex