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 besoeasy/open-skills --skill freqtrade-strategy-backtestgit clone --depth 1 https://github.com/besoeasy/open-skillsWrote 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/besoeasy/open-skills/freqtrade-strategy-backtest)<a href="https://agentmods.dev/skills/besoeasy/open-skills/freqtrade-strategy-backtest"><img src="https://agentmods.dev/badge/skills/besoeasy/open-skills/freqtrade-strategy-backtest/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/besoeasy/open-skills/freqtrade-strategy-backtest"><img src="https://agentmods.dev/badge/skills/besoeasy/open-skills/freqtrade-strategy-backtest.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 | $0.00073 | $0.01238 |
| Opus 5 | $0.00036 | $0.00619 |
| Sonnet 5 | $0.00015 | $0.00248 |
| Haiku 4.5 | $0.00007 | $0.00124 |
Grade A, and why
freqtrade-strategy-backtest 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 7d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Freqtrade Strategy Backtest
Run reproducible freqtrade backtests from local feather/JSON data and produce an apples-to-apples comparison of candidate strategies. Outcome: summary metrics table (profit %, Sharpe, profit factor, exit breakdown) per strategy over the same timerange.
Quick quality checklist
namematches folder name exactly (kebab-case)- Commands tested against freqtrade 2025+ venv installs
- Uses freqtrade built-ins only, no paid data services
- No personal paths, keys, or exchange credentials in examples
When to use
- Use case 1: "Test this new strategy before going live"
- Use case 2: "Compare my current strategy vs a proposed one"
- Use case 3:
ERROR - Pairlist Handlers ... do not support backtesting
Required tools / APIs
- freqtrade CLI in project venv
- Locally downloaded OHLCV data (
user_data/data/<exchange>/*.feather)
Download data if missing:
VENV/bin/freqtrade download-data --config user_data/config.json --userdir user_data \
--timeframe 3m --timerange 20260501- --pairs BTC/USDT ETH/USDT
Skills
static_pairlist_override
Live configs with VolumePairList/AgeFilter/etc. cannot backtest. Never edit the live config — overlay a minimal override config instead:
cat > user_data/config.backtest.json <<'EOF'
{
"pairlists": [
{
"method": "StaticPairList"
}
]
}
EOF
# Later -c files override earlier ones; live config stays untouched
VENV/bin/freqtrade backtesting \
--config user_data/config.json \
--config user_data/config.backtest.json \
--userdir user_data \
--strategy <StrategyName> \
--timeframe 3m \
--timerange YYYYMMDD-YYYYMMDD \
--pairs BTC/USDT ETH/USDT SOL/USDT
compare_candidates
Run each strategy with identical --timeframe, --timerange, and --pairs, then diff the SUMMARY METRICS blocks:
for S in StrategyA StrategyB; do
VENV/bin/freqtrade backtesting \
--config user_data/config.json --config user_data/config.backtest.json \
--userdir user_data --strategy "$S" --timeframe 3m \
--timerange YYYYMMDD-YYYYMMDD --pairs BTC/USDT ETH/USDT \
> "/tmp/${S}_backtest.log" 2>&1
done
grep -h "Total profit %\|Sharpe\|Profit factor\|Market change" /tmp/*_backtest.log
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.
- 7d ago First seen · 133 lines · 73 tokens per session scan A 10c7d06d1410
freqtrade-strategy-backtest is a skill published in the GitHub repository besoeasy/open-skills (132 stars, last pushed 7d ago), licensed MIT. It adds 73 tokens to every session and 1,238 once invoked, about $0.0004 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 2026-09-05.
Other skills, from other repositories
expense-review-policy
Review invoices and contracts against accounts-payable policy before human approval.
stripe-link-wallet
Agent wallet on the Stripe Link CLI (link-cli). Connect the wallet, then buy, purchase and pay for things on the user's behalf via approved spend requests, one-time-use cards, and 402 / Machine Payment Protocol (MPP) payments.
memstack-business-invoice-generator
Use this skill when the user says 'invoice', 'generate invoice', 'create invoice', 'bill client', 'line items', 'payment terms', or needs professional invoices with tax calculations and payment instructions. Do NOT use for contracts or financial projections.
memstack-business-financial-model
Use this skill when the user says 'financial model', 'projections', 'revenue forecast', 'unit economics', 'break-even', 'cash flow', or mentions MRR, churn, CAC, LTV, or runway. Builds monthly projections with scenario modeling. Do NOT use for pricing strategy or invoice generation.
memstack-business-freelancer-toolkit
Use when the user says 'track my time', 'freelancer invoice', 'billable hours', 'time tracking', 'freelance finances', 'client billing', 'project hours', or needs invoicing, time tracking, or analytics patterns for freelance work. Do NOT use for general invoice templates or proposal writing.
fin-pulse
Track finance headlines, daily market radar, and source-backed financial news through Fin Pulse.