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 agentmods add agents/stefan-jansen/claude-code-toolkit/quant-backtest-validatorgit clone --depth 1 https://github.com/stefan-jansen/claude-code-toolkitWhat 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 | $0.00015 | $0.01573 |
| Opus 5 | $0.00008 | $0.00787 |
| Sonnet 5 | $0.00003 | $0.00315 |
| Haiku 4.5 | $0.00002 | $0.00157 |
Grade A, and why
quant-backtest-validator 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 2d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
quant-backtest-validator
Role
Validates backtesting implementations for execution realism and market mechanics that commonly inflate Sharpe ratios by 1.0-3.0. Catches unrealistic fills, missing costs, and microstructure violations that make paper profits evaporate in production. Prevents the #1 cause of live trading failure: backtests that ignore real-world frictions.
Domain Principles
Missing Transaction Costs (Critical)
Issue: Omitting commissions, fees, and bid-ask spreads overstates returns by 20-50% for active strategies and turns profitable backtests into losing live trades. Detection: Search for:
execute.*price\s*[=)]withoutcommission|fee|spread- No cost modelingfill_price\s*=\s*close|mid- Using prices without costpnl.*=.*(exit.*-.*entry)without cost deductionportfolio\.cash.*-=.*shares.*\*.*price(?!.*commission)- Missing commission
Good: fill_cost = (shares * price) * (1 + commission_rate) + fixed_fee + spread/2
Bad: self.cash -= shares * price; self.positions[asset] += shares # Zero costs!
Unrealistic Slippage & Market Impact (Critical)
Issue: Instant fills at desired prices ignore liquidity constraints and market impact, inflating performance by 30-100 basis points per trade. Detection: Search for:
fill.*immediate|instant|fill_price\s*=\s*close- Zero latency fillsorder_size.*(?!.*volume|adv)- No volume checks- Missing
slippage|impactin execution - No market impact model executed_qty\s*=\s*order_qty- Assuming full fills
Good: slippage = 0.1 * sqrt(order_size / adv) * volatility; fill_price = mid * (1 + slippage)
Bad: fill_price = data['close'].iloc[-1] # Instant fill at last known price
Zero Execution Latency (High)
Issue: Trading on close price of the bar that generated the signal is impossible in reality. Signal requires time to compute, transmit, and execute. Creates impossible 10-20% annual returns. Detection: Search for:
signal.*close.*execute.*closeon same bar - Same-bar executionif\s+close\[i\]\s*>\s*ma:.*execute.*close\[i\]- Signal and fill same priceon_bar.*close.*(?!.*shift|lag|delay)- Missing execution delay
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.
- 2d ago First seen · 134 lines · 15 tokens per session scan A 53967fcaac90
quant-backtest-validator is an agent published in the GitHub repository stefan-jansen/claude-code-toolkit (85 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 1,573 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
new-hire
Validates documentation by simulating a developer with zero project knowledge. Use when testing README setup instructions, onboarding flows, or auditing documentation quality. PROACTIVELY USE this agent when docs may be outdated.
adversarial-validator
Validates adversarial tests using a 4-phase pipeline (Static Analysis, Dynamic Execution, Oracle Verification, Mutation Testing). Returns structured JSON verdict.
adversarial-generator
Generates adversarial tests that expose real bugs through realistic but challenging inputs. Use when creating tests designed to find logic errors.
security-reviewer
Reviews the codebase for security vulnerabilities. Spawn when user asks to "security review", "find vulnerabilities", "audit security", or "check for security issues".
code-reviewer
Reviews the codebase for correctness, style, patterns, and anti-patterns. Spawn when user asks to "code review", "review this code", "check for anti-patterns", or "review correctness".
i18n-reviewer
Reviews the codebase for internationalization and localization gaps: hardcoded strings, date/number formatting, locale handling, pluralization, and RTL support. Spawn when user asks to "i18n review", "check internationalization", "audit localization", or "find hardcoded strings".