agentrigs
+ submit rig
~ / rigs / osauer / canary

osauer/canary

Canary is a local risk desk for your brokerage account: daily brief, portfolio and market evidence, read-only MCP tools, CLI, paired app and a Go client. Runs with Interactive Brokers today; the broker layer is its own package. Gated broker

↗ GitHub ★ 8 mit updated 1d ago project Claude CodeCodex Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~4.0k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
2/5
No YOLO mode · Sandbox or ask-first rules · details

Copy this rig

# review before running: this installs third-party code
$ npx degit osauer/canary/.claude ./rig-canary  # 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 osauer/canary/.agents/skills/canary-harness .claude/skills/canary-harness
$ npx degit osauer/canary/.agents/skills/canary-preview .claude/skills/canary-preview
$ npx degit osauer/canary/skills/canary .claude/skills/canary

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 *)"
    ]
  }
}

MCP servers (1)

serversourceest. tokens
canary local / custom 2.5k

Skills (3)

canary-harnesscanary-previewcanary

Hooks (1)

eventmatcherruns
SessionStart*bash "$CLAUDE_PROJECT_DIR/scripts/ci-status.sh"

Similar rigs

CommsConnectgmbh/claude-starter-kit
Claude Code Starter-Kit auf Deutsch: Skills, Agents, CLAUDE.md-Vorlagen & ein 10-Minuten-Setup für alle, die gerade mit Claude Code anfangen.
★ 0 setup Claude Code 12 skills 2 agents 1d ago
Skill Collector 815 tok ·
joi-fairshare/agentic-workflow
Portable Claude Code workflow toolkit: skills, config, repo bootstrapper, and MCP bridge for multi-agent communication
★ 4 project Claude CodeCodexCursor 1 mcp 47 skills today
Skill Collector 7.6k tok ·
FlorianBruniaux/claude-code-plugins
Production-ready Claude Code plugins: skills, hooks, agents, slash commands, and MCP templates.
★ 42 collection Claude Code 8 mcp 47 skills 1mo ago
MCP Hoarder 23.2k tok ·
greglas75/zuvo
Auto-activating, multi-agent skill ecosystem for Claude Code, Codex, and Cursor. 51 skills, 26 agents, quality gates, knowledge store, adversarial review, content writing & optimization.
★ 8 collection Claude CodeCodexGemini CLI 57 skills today
Skill Collector 8.7k tok ·
copied ✓