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 QuantJourneyOrg/quantjourney-bt --skill qj-config-helpergit clone --depth 1 https://github.com/QuantJourneyOrg/quantjourney-btWrote 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/quantjourneyorg/quantjourney-bt/qj-config-helper)<a href="https://agentmods.dev/skills/quantjourneyorg/quantjourney-bt/qj-config-helper"><img src="https://agentmods.dev/badge/skills/quantjourneyorg/quantjourney-bt/qj-config-helper/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/quantjourneyorg/quantjourney-bt/qj-config-helper"><img src="https://agentmods.dev/badge/skills/quantjourneyorg/quantjourney-bt/qj-config-helper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.00752 |
| Opus 5.5 | $0.00000 | $0.00301 |
| Sonnet 5.5 | $0.00000 | $0.00150 |
| Haiku 4.5 | $0.00000 | $0.00075 |
Grade A, and why
qj-config-helper 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QuantJourney Config Helper
Use this skill to configure a QuantJourney Backtester — choose the right
parameters, rebalance policy, risk overlay, granularity, and report settings.
Core parameters
strategy = MyStrategy(
strategy_name="...", # names the report folder
instruments=["AAPL", "MSFT", ...], # or a market-neutral pair, or a wide universe
backtest_period={"start": "2015-01-01", "end": "2025-01-01"},
source="yfinance", # intraday requires yfinance
granularity="1d", # 1d | 1m | 5m | 15m | 30m | 1h
execution_mode="weights", # weights | orders
initial_capital=100_000,
max_position_size=0.25, # per-name cap; use 1.0 for long/short legs
indicators_config=[...], # declares SMA/EMA/RSI features
benchmark_symbol="^GSPC",
reporting_frequency="daily", # daily | weekly | monthly | quarterly
theme_plots="quantjourney", # or bloomberg, dark, academic, minimal
show_text_reports=True, save_portfolio_plots=True,
)
Rebalance policy (weight mode)
Compose triggers with RebalancePolicy(...):
frequency—"D","W"(+weekday),"BME","BQE","BYE", orNone.drift_threshold(+drift_type) — rebalance only when a weight drifts past X.tracking_error_threshold(+tracking_error_window) — rebalance vs benchmark TE.rebalance_on_signal_change(+signal_change_threshold) — trade only on flips.max_drawdown_trigger(+max_drawdown_action,circuit_breaker_cooldown_days) — circuit breaker.max_annual_turnover— turnover budget (cost gate).partial_rebalance— trade only the drifted names.
Risk overlays (weight mode)
Attach via risk_model=; applied between weights and rebalance:
VolTargetModel(target_vol=0.10, lookback=63, max_leverage=1.5)RiskParityModel(lookback=63)— equal risk contributionInverseVolModel(lookback=63)PositionLimitModel(max_weight=0.25)RiskModelChain([...])— apply several in order
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.
- 2mo ago First seen · 65 lines · 0 tokens per session scan A d1dc3c84d6d2
qj-config-helper is a skill published in the GitHub repository QuantJourneyOrg/quantjourney-bt (581 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 752 tokens. 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 2026-08-30.
qj-config-helper compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| qj-config-helperQuantJourneyOrg/quantjourney-bt | Skill | 581 | 2d ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| tushareHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 79 | Claude Code, Codex |
| correlation-analysisHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 57 | Claude Code, Codex |
| social-media-intelligenceHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 28 | Claude Code, Codex |
| credit-analysisHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 36 | Claude Code, Codex |
| etf-analysisHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 39 | Claude Code, Codex |
| geopolitical-riskHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 34 | Claude Code, Codex |