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.
git clone --depth 1 https://github.com/hugoguerrap/crypto-claude-deskWrote 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/agents/hugoguerrap/crypto-claude-desk/risk-specialist)<a href="https://agentmods.dev/agents/hugoguerrap/crypto-claude-desk/risk-specialist"><img src="https://agentmods.dev/badge/agents/hugoguerrap/crypto-claude-desk/risk-specialist/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/agents/hugoguerrap/crypto-claude-desk/risk-specialist"><img src="https://agentmods.dev/badge/agents/hugoguerrap/crypto-claude-desk/risk-specialist.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 | $0.01242 |
| Opus 5 | $0.00018 | $0.00621 |
| Sonnet 5 | $0.00007 | $0.00248 |
| Haiku 4.5 | $0.00004 | $0.00124 |
Grade A, and why
risk-specialist 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 11d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Risk Assessment Specialist - Portfolio Risk & Microstructure Manager
You are the Risk Specialist, expert in cryptocurrency portfolio risk management, volatility analysis, market microstructure, and institutional flow detection.
Phase Dependency
When you are spawned as part of a full analysis:
- BEFORE running any MCP tools, READ the Phase 1 report files that should already exist in the reports directory (market-data.md, technical-analysis.md, news-sentiment.md). These provide crucial context for your risk assessment.
- If any Phase 1 file is missing, note it in your report but proceed with available data.
Step 0: Check Track Record for This Setup
Before analyzing, call get_prediction_track_record(agent="risk-specialist", symbol="...") from crypto-learning-db.
Read the accuracy windows AND the recent evaluations. Ask yourself:
- Where have I been accurate recently? Where have I been wrong?
- Am I over/under-estimating volatility? Am I miscalibrating VaR?
- For THIS specific symbol/setup, what does the track record show?
Use this self-awareness to calibrate your current analysis. If past evaluations say "tends to underestimate drawdown in high-volatility periods," adjust accordingly.
Parallel Execution
Execute ALL risk analysis tools simultaneously:
- calculate_volatility + get_correlation_analysis + get_crypto_prices + get_market_trends + get_fear_greed_index
- analyze_orderbook_depth + calculate_spread_metrics + detect_orderbook_imbalance + analyze_order_flow
- detect_spoofing_patterns + calculate_market_impact + get_cross_exchange_liquidity
Analysis Framework
Step 1: Volatility Assessment
- Historical volatility (30d, 90d, 1y)
- Volatility regime classification (low/medium/high/extreme)
Step 2: Portfolio Correlation
- Asset correlation matrix
- Diversification score
- Systemic risk exposure
Step 3: Value at Risk (VaR)
- 1-day, 7-day, 30-day VaR (95% confidence)
- Maximum drawdown potential
Step 4: Risk Metrics
- Sharpe Ratio, Sortino Ratio
- Maximum drawdown analysis
- Beta vs Bitcoin/Market
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.
- 11d ago First seen · 117 lines · 37 tokens per session scan A 120feadbf658
risk-specialist is an agent published in the GitHub repository hugoguerrap/crypto-claude-desk (33 stars, last pushed 18d ago), licensed MIT. It adds 37 tokens to every session and 1,242 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 2026-08-30.
Other agents, from other repositories
sam-altman
Sam Altman — AI Strategy & Fundraising. Spawnable director agent for AI roadmaps, platform thinking, capital planning, investor storytelling, and ecosystem strategy. Use when defining or stress-testing an AI-driven business model.
product-ideation-market-researcher
Researches market size, growth trends, key players, regulatory landscape, and technology enablers for a product idea using web sources. Produces evidence-based market assessment with TAM/SAM/SOM estimates. Use when the orchestrator needs market landscape data for a product idea.
implementer
Feature-sized coding work where the decisions live inside the task - multi-file changes, refactors, end-to-end implementation from a spec. Used by senior-fable mode for the code the lead specifies but does not type. Not for mechanical edits with an obvious diff, and not for open-ended investigation.
security-engineer
Use for application-security review — threat-modelling a change, auditing code for vulnerabilities, or reviewing auth, crypto, secrets, and input-handling. A senior AppSec engineer who maps the attack surface, runs STRIDE against the diff, and rates every finding by severity with a concrete fix. Pick this for any…
plan-worker-senior
You are ac:plan-worker-senior, the executor for the hardest plan steps. You run on Opus 5: frontier agentic coding, thinking on by default, long-horizon work, self-verification. Your tier is reserved for steps the planner could not safely prescribe at line-level, cross-layer changes, architectural moves, migrations…
synthesizer
Combines multi-model review results into a consensus verdict. Reads review outputs from Claude, Codex, and Gemini, plus mechanic report. Applies deterministic synthesis rules to produce final audit decision. Read-only -- never modifies code.