altrace-dev-role/rashomon
Verify what your Claude Code agent actually did. Rashomon keeps an independent record of every tool call, subagent, failed command, and flags when the agent's summary says all tests pass but something failed. Open-source AI agent verificati
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit altrace-dev-role/rashomon/skills ./rig-rashomon/skills 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 altrace-dev-role/rashomon/plugin/skills/forget .claude/skills/forget $ npx degit altrace-dev-role/rashomon/plugin/skills/report .claude/skills/report $ npx degit altrace-dev-role/rashomon/plugin/skills/status .claude/skills/status $ npx degit altrace-dev-role/rashomon/plugin/skills/stop .claude/skills/stop $ npx degit altrace-dev-role/rashomon/plugin/skills/watch .claude/skills/watch $ npx degit altrace-dev-role/rashomon/skills/rashomon-forget .claude/skills/rashomon-forget $ npx degit altrace-dev-role/rashomon/skills/rashomon-report .claude/skills/rashomon-report $ npx degit altrace-dev-role/rashomon/skills/rashomon-status .claude/skills/rashomon-status $ npx degit altrace-dev-role/rashomon/skills/rashomon-stop .claude/skills/rashomon-stop $ npx degit altrace-dev-role/rashomon/skills/rashomon .claude/skills/rashomon
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (10)
Similar rigs
snofla/claude-jared
Syntax-highlighted, file-based review for Claude.
Minimalist 258 tok · · Q0
robertnowell/marketing-pipeline
Problem-first automated marketing pipeline for open source projects.
Pragmatist 269 tok · · Q0
speedsharmaai/phaseproof
Claude Code plugin: docs, design, build and ship in phases. Code stays locked until you approve, and every phase is checked by an independent reviewer agent on a stronger model.
Pragmatist 485 tok · · Q0
sweetcornna/bunsen
开源 AI 科研工作台:让 Claude Code、Codex 等 Agent 在你自己的 GPU 服务器上做研究。运行记录、结论账本、产物画廊、显卡监控,断线不停。Self-hosted AI research workbench.
Pragmatist 353 tok · · Q0