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 ayggdrasil/options_trading_base --skill callput-agent-mcpgit clone --depth 1 https://github.com/ayggdrasil/options_trading_baseWrote 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/ayggdrasil/options_trading_base/callput-agent-mcp)<a href="https://agentmods.dev/skills/ayggdrasil/options_trading_base/callput-agent-mcp"><img src="https://agentmods.dev/badge/skills/ayggdrasil/options_trading_base/callput-agent-mcp/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/ayggdrasil/options_trading_base/callput-agent-mcp"><img src="https://agentmods.dev/badge/skills/ayggdrasil/options_trading_base/callput-agent-mcp.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 | $0.00036 | $0.01143 |
| Opus 5 | $0.00018 | $0.00571 |
| Sonnet 5 | $0.00007 | $0.00229 |
| Haiku 4.5 | $0.00004 | $0.00114 |
Grade A, and why
callput-option-trader 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 10d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Callput Option Trader (Compact)
Important Runtime Path Rule
<mcp_entry>is a documentation placeholder only.- In real OpenClaw/Claude MCP config, replace it with an absolute local path.
- Do not keep literal
<mcp_entry>inargsat runtime. - Prefer a path without spaces to avoid launcher parsing issues.
Use this skill when the user asks for:
- BTC/ETH options market read
- spread entry (bullish/bearish)
- open position management (close/settle)
One-line Intent
Market analysis -> direction setup -> tradable spread validation -> execution and position adjustment
Canonical MCP Target
- server path:
<mcp_entry> - do not use legacy
/mcp-server/build/index.jsfor new agents - use canonical tool names:
callput_*only
<mcp_entry> means the absolute local path to build/index.js.
Non-Negotiable Rules
callput_get_option_chainsoutput is for leg discovery, not direct single-leg execution.- Never attempt vanilla single-leg trading via MCP.
- Always call
callput_validate_spreadbeforecallput_request_quote. - Trade only if:
status == "Valid"details.maxTradableQuantity > 0
- After broadcast, always call
callput_check_tx_status. - If
cancelled, refresh legs and repeat validation. - For existing positions:
- pre-expiry:
callput_close_position - expired:
callput_settle_position
- pre-expiry:
- Never expose private keys in MCP output.
- Enforce input guards before calls:
callput_approve_usdc.amount > 0callput_check_tx_status.tx_hashmust be 32-byte hexcallput_close_position.addressmust be valid EVM addresscallput_close_position.size > 0callput_settle_positionis only for expired optionscallput_get_option_chains.expiry_datemust match a listed expiry
Context Overflow Guardrails
- Do not keep raw chain responses in long conversation memory.
- Immediately compress tool output into a compact state object and discard raw payload.
- Keep candidate set small:
- max 5 candidate spreads per cycle
- max 6 Greeks lookups per cycle
- Always filter chain queries as tightly as possible:
- set
underlying_asset - set
option_typewhen known - set
expiry_dateonce target tenor is chosen
- set
- Persist only minimal fields across turns:
asset,bias,target_expirycandidate_ids(short list)selected_long_leg_id,selected_short_leg_idvalidation_status,maxTradableQuantitylast_tx_hash,last_tx_status
- During status polling, only store latest status snapshot, not full history.
- If context window grows, drop historical reasoning and re-bootstrap from the compact state object.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .agent/skills/mcp-builder 32 B
- .agent/skills/skill-creator 34 B
- .agents/skills/mcp-builder/LICENSE.txt 11 KB
- .agents/skills/mcp-builder/reference/evaluation.md 21 KB
- .agents/skills/mcp-builder/reference/mcp_best_practices.md 7.2 KB
- .agents/skills/mcp-builder/reference/node_mcp_server.md 28 KB
- .agents/skills/mcp-builder/reference/python_mcp_server.md 25 KB
- .agents/skills/mcp-builder/scripts/connections.py 4.8 KB runs code
- .agents/skills/mcp-builder/scripts/evaluation.py 12 KB runs code
- .agents/skills/mcp-builder/scripts/example_evaluation.xml 1.2 KB
- .agents/skills/mcp-builder/scripts/requirements.txt 29 B
- .agents/skills/mcp-builder/SKILL.md 8.9 KB
- .agents/skills/skill-creator/LICENSE.txt 11 KB
- .agents/skills/skill-creator/references/output-patterns.md 1.8 KB
- .agents/skills/skill-creator/references/workflows.md 818 B
- .agents/skills/skill-creator/scripts/init_skill.py 11 KB runs code
- .agents/skills/skill-creator/scripts/package_skill.py 3.2 KB runs code
- .agents/skills/skill-creator/scripts/quick_validate.py 3.9 KB runs code
- .agents/skills/skill-creator/SKILL.md 18 KB
- .gitignore 78 B
- ARCHITECTURE.md 3.5 KB
- background.png 62 KB
- check_s3_structure.js 701 B runs code
- CONTRIBUTING.md 1.2 KB
- EXAMPLE_OUTPUT.md 3.8 KB
- EXTERNAL_AGENT_GUIDE_KR.md 1.3 KB
- EXTERNAL_AGENT_GUIDE.md 7.4 KB
- frontend/.gitignore 253 B
- frontend/eslint.config.js 616 B runs code
- frontend/index.html 357 B
- frontend/package-lock.json 133 KB
- frontend/package.json 997 B
- frontend/public/vite.svg 1.5 KB
- frontend/README.md 2.5 KB
- frontend/src/App.css 606 B
- frontend/src/App.tsx 132 B
- frontend/src/assets/react.svg 4.0 KB
- frontend/src/ChatboxDemo.tsx 5.1 KB
- frontend/src/components/ui/claude-style-chat-input.tsx 26 KB
- frontend/src/index.css 2.7 KB
- frontend/src/LandingPage.tsx 19 KB
- frontend/src/lib/utils.ts 168 B runs code
- frontend/src/main.tsx 230 B
- frontend/tsconfig.app.json 732 B
- frontend/tsconfig.json 119 B
- frontend/tsconfig.node.json 653 B
- frontend/vite.config.ts 327 B runs code
- index.html 26 KB
- LICENSE 1.0 KB
- MCP_SETUP.md 3.2 KB
- OPENCLAW_SYSTEM_PROMPT.md 2.3 KB
- package-lock.json 71 KB
- package.json 1.4 KB
- README.md 6.7 KB
- src/abis.ts 2.6 KB runs code
- src/check_vault_mapping_v2.ts 1.5 KB runs code
- src/check_vault_mapping.ts 1.8 KB runs code
- src/config.ts 1.8 KB runs code
- src/debug_data.ts 2.7 KB runs code
- src/debug_s3_detailed.ts 2.1 KB runs code
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.
- 10d ago First seen · 115 lines · 36 tokens per session scan A 0fce8a9c7559
callput-option-trader is a skill published in the GitHub repository ayggdrasil/options_trading_base (1 stars, last pushed 6mo ago), licensed MIT. It adds 36 tokens to every session and 1,143 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 2026-08-31.
Other skills, from other repositories
hoodmarkets
Launch, buy, sell, and claim fees for hood.markets tokens on Robinhood Chain (4663) via api.hood.markets. Use for hoodmarkets, hood.markets, $hood, launch token, deploy token, buy token, sell token, claim fees, Bankr Robinhood. NEVER use hood.markets for API POST — use api.hood.markets.
rh-bridge-pro
Advanced LayerZero bridge with liquidity seeding between Base and Robinhood Chain.
rh-earnings-agent
Automated earnings play agent for tokenized stocks on Robinhood Chain.
rh-stock-scanner
Real-time momentum, volume, correlation, and opportunity scanner for tokenized stocks on Robinhood Chain.
rh-yield-optimizer
Smart yield optimization engine using tokenized stocks as collateral on Robinhood Chain.
base-l2-agent-kit
MCP server providing Base L2 DeFi tools for AI agents.