investment-autoresearch:parse

investment-autoresearch:parse is a skill for Claude Code from lucemia/investment-autoresearch. It costs 37 tokens per session (1,777 once invoked), scanned A, original, MIT.

A converter for turning autoresearch Markdown files into structured JSON. Autoresearch is repeated testing of investment strategies; the converter also runs walk-forward backtests, which test a strategy on successive historical periods, to supply trusted performance figures.

In plain words
What is it for?
Use it to prepare ticker research for reports or slides, including strategy names, findings, rejected ideas, hypotheses, and backtested metrics such as annualized return and maximum drawdown.
Why use it?
It separates written research notes from numbers that must be calculated, avoiding reliance on inconsistent return or drawdown figures in the Markdown.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the investment-autoresearch plugin — 4 skills shipped together

Good fit Use it to prepare ticker research for reports or slides, including strategy names, findings, rejected ideas, hypotheses, and backtested metrics such as annualized return and maximum drawdown.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lucemia/investment-autoresearch/parse
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 lucemia/investment-autoresearch --skill parse
Clone the repo
git clone --depth 1 https://github.com/lucemia/investment-autoresearch

Made for: Claude Code.

Or install investment-autoresearch, the plugin that ships this one along with the rest of its 4 skills.

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 investment-autoresearch:parse

README.md
[![agentmods](https://agentmods.dev/badge/skills/lucemia/investment-autoresearch/parse/github.svg)](https://agentmods.dev/skills/lucemia/investment-autoresearch/parse)
Your own site
<a href="https://agentmods.dev/skills/lucemia/investment-autoresearch/parse"><img src="https://agentmods.dev/badge/skills/lucemia/investment-autoresearch/parse/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 investment-autoresearch:parse

Your own site · 80×15
<a href="https://agentmods.dev/skills/lucemia/investment-autoresearch/parse"><img src="https://agentmods.dev/badge/skills/lucemia/investment-autoresearch/parse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,777 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 $0.00037 $0.01777
Opus 5 $0.00018 $0.00889
Sonnet 5 $0.00007 $0.00355
Haiku 4.5 $0.00004 $0.00178

Measured 9d ago against content hash 7480ddef1d5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

investment-autoresearch:parse 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.

skills/parse/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autoresearch Parse

Extracts structured JSON from autoresearch markdown outputs for a given ticker, then always runs walk-forward backtests to populate authoritative numeric values.

Two-Phase Process

Phase 1: Parse markdown → text fields (strategy name, insights, rejections, hypotheses)
Phase 2: Run your backtest command → numeric fields (cagr, max_drawdown, walk_forward RA)

Never trust markdown numbers for cagr or max_drawdown. Agents write Return [%] (total return) and Return (Ann.) [%] (CAGR) interchangeably. Only backtesting gives the authoritative annualized CAGR.

Input Files

For a given ticker, two file types exist under archive/{ticker}-autoresearch-v{N}/:

File Contains
verified_insights.md Cumulative state: current best, insights, rejections, open hypotheses
AGENT_R{N}_RESULTS.md Per-round: hypothesis, results table, key learnings

Output JSON Schema

{
  "ticker": "SOXL",
  "research_summary": {
    "rounds_completed": 40,
    "agents_run": 42,
    "strategies_tested": 630
  },
  "current_best": {
    "strategy_name": "R15 W7 + min hold 10 days",
    "parameters": {},
    "cagr": 104.5,
    "max_drawdown": -31.8,
    "sharpe": null,
    "robustness_score": 0.710,
    "walk_forward": {
      "5y": { "cagr": 104.5, "ra": 5.86 },
      "3y": { "cagr": 98.2,  "ra": 5.51 },
      "2y": { "cagr": 110.3, "ra": 6.19 },
      "1y": { "cagr": 88.7,  "ra": 4.98 }
    },
    "min_ra_across_periods": 4.98
  },
  ...
}

cagr and all walk_forward values come from Phase 2 backtesting, not markdown parsing.

Phase 1 — Parse Markdown

ticker

From the verified_insights.md header line: # Verified Insights — {TICKER} ...

research_summary

  • rounds_completed: "after N rounds" or count of AGENT_R*_RESULTS.md files
  • strategies_tested: "N+ strategies evaluated across N rounds"
  • agents_run: same as rounds_completed unless stated otherwise

current_best (text fields only)

Prefer the risk-adjusted / lowest MaxDD champion:

  • strategy_name: bolded strategy label
  • parameters: extract from markdown if listed; else {}
  • Leave cagr, max_drawdown, walk_forward as null — Phase 2 will fill them

Read the full file on GitHub · 180 lines

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. 9d ago First seen · 180 lines · 37 tokens per session scan A 7480ddef1d5b

Subscribe to this mod's changes

investment-autoresearch:parse is a skill published in the GitHub repository lucemia/investment-autoresearch (4 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 1,777 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.

Related

Other skills, from other repositories