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-risk-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 | $0.01943 |
| Opus 5 | $0.00008 | $0.00971 |
| Sonnet 5 | $0.00003 | $0.00389 |
| Haiku 4.5 | $0.00002 | $0.00194 |
Grade A, and why
quant-risk-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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
quant-risk-validator
Role
Validates risk management infrastructure and deployment safeguards that prevent catastrophic losses and ensure production stability. Catches missing kill switches, improper position sizing, and governance failures that cause 90% of quant fund blowups. Production-ready code must have hard stops, not hope.
Domain Principles
Lack of Reproducibility (Critical)
Issue: Non-deterministic behavior from unseeded randomness makes debugging impossible and hides critical bugs until production. Cannot reproduce backtest results or verify fixes. Detection: Search for:
np\.random\.rand|randn|choicewithout precedingseed|RandomState- Unseeded numpyrandom\.withoutrandom\.seed- Unseeded Python randomLGBMClassifier|RandomForest|KMeans.*\((?!.*random_state)- ML without seed- Model training without
PYTHONHASHSEEDset - Non-deterministic hash
Good: np.random.seed(42); random.seed(42); os.environ['PYTHONHASHSEED'] = '42'; model = LGBMClassifier(random_state=42)
Bad: model = RandomForestRegressor().fit(X, y) # Non-reproducible results
Missing Hard Risk Limits (Critical)
Issue: No maximum drawdown or daily loss cutoff allows malfunctioning strategies to wipe out accounts. The #1 cause of total capital loss. Detection: Search for:
portfolio\.updatewithout subsequentdrawdown.*>.*limitcheck - No drawdown stop- Missing
max_loss|stop_loss|max_drawdownvariables - No limits defined while.*tradewithoutif.*loss.*>.*limit.*break- No exit condition
Good: if portfolio.drawdown > MAX_DRAWDOWN_LIMIT: liquidate_all(); halt_trading(); send_alert()
Bad: portfolio.update_pnl() # No safety checks, unlimited losses possible
Static Position Sizing (High)
Issue: Fixed dollar positions ignore volatility, causing 5-10x leverage swings during regime changes and margin calls. Detection: Search for:
position\s*=\s*\d+|capital.*\*.*0\.\d+- Fixed position sizesize.*capital.*\/.*pricewithoutvolatility|atr|risk- No vol scaling- Missing
kelly|risk_parity|vol_targetmethods - No dynamic sizing
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 · 162 lines · 15 tokens per session scan A 1fa8f93c0a0d
quant-risk-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 1,943 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
Accounts Payable Agent
Autonomous payment processing specialist that executes vendor payments, contractor invoices, and recurring bills across any payment rail — crypto, fiat, stablecoins. Integrates with AI agent workflows via tool calls.
stock-balance-sheet-reviewer
Specialist for US-stock balance-sheet health review — leverage (Net Debt/EBITDA), liquidity (current ratio, cash runway), goodwill concentration and impairment history, working capital trends (DSO, inventory days), off-balance-sheet items (commitments, contingencies), and pension underfunding. Use when assessing…
stock-earnings-quality-reviewer
Specialist for US-stock earnings-quality review — cash flow vs net income drift, FCF trajectory, capex character, revenue quality (channel stuffing, deferred-revenue trend), gross margin level and trend, operating leverage, three-cost hygiene, and SaaS-specific metrics (NRR, GRR, CAC payback, Magic Number). Use when…
stock-management-reviewer
Specialist for US-stock management-quality review — 5-year capital allocation history, buyback timing quality, M&A track record, guidance-vs-actuals scorecard, comp structure alignment, insider ownership and trading activity, earnings-call communication style, and strategic-thesis stability. Use when analyzing the…
Financial Analyst
Analyzes financial data, generates reports, and provides business insights.
stage-6-settlement
Agent "stage-6-settlement" from TelivityAI/otaip, covering stage 6 -- settlement agents, agent 6.1 -- refund processing, agent 6.2 -- adm prevention, agent 6.3 -- adm/acm processing and agent 6.4 -- customer communication.