trading-bot
Skill8 starsChanged 14 days agoMITView on GitHub
Use when the user asks what the trading agent can do, how to use it, or how risk controls work. The mangrove-agent operating rules cover server workflow discovery and local execution, how to present and handle wallets without secrets ever entering chat, and which risk controls already run in the engine and the agent. Load it before any strategy, backtest, sweep, wallet, balance, swap, Kraken or live-trading work, and whenever the user asks what the bot can do or how it keeps funds safe. Trigger with phrases such as "what can this bot do", "how does the bot manage risk", or "help me use the trading agent".
1 other project uses a version of this.
Adopted by
Most recently taken up by
- Yahmez3/Claude-Skillstheir own version, first seen Apr 15, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- Yahmez3/Claude-Skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- audit-securitySkill
- check-alignmentSkill
- connect-krakenSkill
- setup-krakenSkill
- setup-robinhoodSkill
- tool-specSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Follow these three documents.
- Distinctive: line 36
Search for the tools needed for this task.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Operating the Mangrove trading agent
Follow these three documents. If their complete contents are already loaded by the native rules loader or shared bundle, do not read them again. Otherwise read the missing documents in full before trading. They are the contract for every trading action this agent takes.
${CLAUDE_PLUGIN_ROOT}/.claude/rules/trading-bot-workflow.md— how to load live server workflow instructions over MCP.${CLAUDE_PLUGIN_ROOT}/.claude/rules/wallet-presentation.md— creating, importing and presenting wallets; separate-UID custody and direct human administration; testnet-first defaults; strict transaction intent and independent signing limits.${CLAUDE_PLUGIN_ROOT}/.claude/rules/risk-management.md— engine-side per-strategy gates and the agent-side portfolio kill switch, so you explain blocked trades correctly and never rebuild a control that already exists.
Reading them inside the plugin
Those documents were written for a git clone of the repo. When running as the installed plugin:
- Tool names are
mcp__plugin_mangrove-agent_mangrove-agent__<tool>, notmcp__mangrove-agent__<tool>. Search for the tools needed for this task; load their actual schemas without importing the entire catalog into context. - Scripts written as
./scripts/<name>.share at${CLAUDE_PLUGIN_ROOT}/scripts/<name>.sh. The user runs them in their own terminal, never through you. ./agent-data/andserver/src/config/local-config.jsonlive under~/.mangrove-agent/(agent-data/andconfig/), which survives plugin updates.- There is no
./scripts/setup.shstep: the plugin installs and starts the agent itself at session start. If the agent is down, check~/.mangrove-agent/agent-data/bootstrap.log.
In a git clone these rules already load automatically from .claude/rules/; the paths in them are
relative to the repo root.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

