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 skills add lucemia/investment-autoresearch --skill parsegit clone --depth 1 https://github.com/lucemia/investment-autoresearchWrote 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/skills/lucemia/investment-autoresearch/parse)<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.
<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>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 | $0.01777 |
| Opus 5 | $0.00018 | $0.00889 |
| Sonnet 5 | $0.00007 | $0.00355 |
| Haiku 4.5 | $0.00004 | $0.00178 |
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.
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 filesstrategies_tested: "N+ strategies evaluated across N rounds"agents_run: same asrounds_completedunless stated otherwise
current_best (text fields only)
Prefer the risk-adjusted / lowest MaxDD champion:
strategy_name: bolded strategy labelparameters: extract from markdown if listed; else{}- Leave
cagr,max_drawdown,walk_forwardasnull— Phase 2 will fill them
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.
- 9d ago First seen · 180 lines · 37 tokens per session scan A 7480ddef1d5b
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.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.