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 hugoguerrap/crypto-claude-desk --skill close-tradegit 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/skills/hugoguerrap/crypto-claude-desk/close-trade)<a href="https://agentmods.dev/skills/hugoguerrap/crypto-claude-desk/close-trade"><img src="https://agentmods.dev/badge/skills/hugoguerrap/crypto-claude-desk/close-trade/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/hugoguerrap/crypto-claude-desk/close-trade"><img src="https://agentmods.dev/badge/skills/hugoguerrap/crypto-claude-desk/close-trade.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 | $0.00528 |
| Opus 5 | $0.00018 | $0.00264 |
| Sonnet 5 | $0.00007 | $0.00106 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
close-trade 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Close Trade & Post-Mortem
Close trade $ARGUMENTS and run a post-mortem analysis.
Workflow
Step 1: Close the Trade
Delegate using the Task tool with subagent_type: general-purpose and model: opus:
"You are the portfolio-manager agent. Read agents/portfolio-manager.md for your decision framework. Close trade $ARGUMENTS. If a price is specified after 'at', use that as exit price. Otherwise, get the current market price using get_exchange_prices() from crypto-exchange MCP. Call close_trade(trade_id='...', exit_price=..., close_reason='...') from crypto-learning-db MCP. PnL, portfolio balance, and stats are updated automatically. Do NOT use the Edit tool."
Step 2: Post-Mortem Analysis
After the trade is closed, delegate using the Task tool with subagent_type: general-purpose and model: opus:
"You are the learning-agent. Read agents/learning-agent.md for your analysis framework. Run a post-mortem analysis on the recently closed trade $ARGUMENTS. Call query_trades(status='closed', limit=1) from crypto-learning-db to get the trade data. Read any related reports from data/reports/. Analyze what worked, what didn't, and provide specific recommendations for improvement. Do NOT use the Edit tool."
Step 3: Validate Predictions & Update Patterns
After the post-mortem, delegate using the Task tool with subagent_type: general-purpose and model: opus:
"You are the learning-agent. Validate all predictions for trade $ARGUMENTS. Call query_predictions(trade_id='...') from crypto-learning-db to find all predictions tied to this trade. Compare each prediction against the actual outcome. Call validate_prediction() for each one with a detailed NL evaluation of how close the prediction was and what we can learn. Then call upsert_pattern() to update the pattern library with the setup from this trade. Do NOT use the Edit tool."
Step 4: Present Results
Show:
- Trade closure summary (entry, exit, PnL)
- Post-mortem analysis
- Prediction accuracy (how many correct vs incorrect, with evaluations)
- Pattern identified (win rate, recommendation)
- Lessons learned
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 · 48 lines · 0 tokens per session scan A 481ca8fec7c1
close-trade is a skill 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 528 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 skills, from other repositories
pricing-refresh
Refresh or verify the hermit cost rate table against Anthropic's live pricing. Use when the operator says "refresh pricing", "verify pricing", "is the rate table current", "new model pricing", or asks whether scripts/lib/pricing.ts matches current Codex rates. Maintainer-only; never autonomous, never a routine, never…
fintech-expert
Expert in financial technology, payment processing, open banking APIs, PSD2, blockchain in finance, robo-advisors, and RegTech. Use when the user mentions payments, open banking, PSD2, blockchain, cryptocurrency, or robo advisor, or when the task involves Payment Processing, Blockchain in Finance, Payment Security, or…
moss-trade-bot-factory-1.0.25-beta
A tool for turning a trading idea written in everyday language into a cryptocurrency trading bot. It can run local tests on past market data, with optional checks and simulated trades through external platforms.
moss-trade-bot-factory
A tool for creating cryptocurrency trading bots from a description of the coin, testing period, and strategy style. It uses included Hyperliquid market-data files for local backtesting and strategy evolution.
moss-trade-bot-factory
A tool for creating cryptocurrency trading bots from a described currency, date range, and strategy style. It uses built-in Hyperliquid CSV market-data files for local backtesting and strategy evolution, and can optionally upload a bot for verification or simulated live trading.
moss-trade-bot-factory-1.0.3
A tool for turning a trading idea written in everyday language into a cryptocurrency trading bot. It can run local tests on past market data, with optional checks and simulated trades through external platforms.