agentrigs
+ submit rig
~ / rigs / mafftopia / trade-stories

mafftopia/trade-stories

Trade Stories DSL

↗ GitHub ★ 6 MIT updated 29d ago project Claude Code Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~644 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit mafftopia/trade-stories/.claude ./rig-trade-stories  # inspect, then merge into .claude/

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit mafftopia/trade-stories/.claude/skills/lint-story .claude/skills/lint-story
$ npx degit mafftopia/trade-stories/.claude/skills/verify-story .claude/skills/verify-story
$ npx degit mafftopia/trade-stories/.claude/skills/write-story .claude/skills/write-story
$ curl -fsSL --create-dirs -o .claude/agents/new-story-reviewer.md https://raw.githubusercontent.com/mafftopia/trade-stories/main/.claude/agents/new-story-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/story-writer.md https://raw.githubusercontent.com/mafftopia/trade-stories/main/.claude/agents/story-writer.md

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (3)

lint-storyverify-storywrite-story

Subagents (2)

new-story-reviewerCheck a Trade Story that /write-story has just written, before the trader sees it. Runs the checks verify-story and lint-story would, and reports rather than fixes.
story-writerCompose and write the Trade Story file from the answers /write-story has already collected. Invoked by /write-story, and reports back to it rather than to the trader.

Similar rigs

heyJordanParker/dotfiles
—
★ 22 setup Claude Code 109 skills 2d ago
Skill Collector 6.4k tok ·
anomalyco/opencode
The open source coding agent.
★ 212k project Codex 2 skills 1d ago
Pragmatist 4.2k tok ·
DietrichGebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
★ 155k project CodexCursorCopilot 6 skills 4d ago
Pragmatist 1.6k tok ·
Shubhamsaboo/awesome-llm-apps
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
★ 141k project Claude CodeCodex 1 mcp 3 skills 9d ago
Pragmatist 4.2k tok ·
copied ✓