blundergoat/goat-flow
A structured workflow system for AI coding agents - harness engineering, execution loop, skills, hooks, and a learning loop. Works with Claude Code, Codex, Antigravity CLI, Copilot.
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
GUARDRAILS
4/5
Blocks destructive commands · Protects secrets · Pre-tool screening hook · No YOLO mode · details
Copy this rig
# review before running: this installs third-party code
$ npx degit blundergoat/goat-flow/.claude ./rig-goat-flow # 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 blundergoat/goat-flow/.agents/skills/goat-clarity .claude/skills/goat-clarity $ npx degit blundergoat/goat-flow/.agents/skills/goat-critique .claude/skills/goat-critique $ npx degit blundergoat/goat-flow/.agents/skills/goat-debug .claude/skills/goat-debug $ npx degit blundergoat/goat-flow/.agents/skills/goat-plan .claude/skills/goat-plan $ npx degit blundergoat/goat-flow/.agents/skills/goat-qa .claude/skills/goat-qa $ npx degit blundergoat/goat-flow/.agents/skills/goat-review .claude/skills/goat-review $ npx degit blundergoat/goat-flow/.agents/skills/goat-security .claude/skills/goat-security $ npx degit blundergoat/goat-flow/.agents/skills/goat .claude/skills/goat
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Bash(*git commit*)",
"Bash(*git push*)",
"Read(**/.env)",
"Read(**/.env.local)",
"Read(**/.env.development)",
"Read(**/.env.production)",
"Read(**/.env.staging)",
"Read(**/.env.test)",
"Read(**/.envrc)",
"Read(**/.env.*.local)",
"Edit(**/.env)",
"Edit(**/.env.local)",
"Edit(**/.env.development)",
"Edit(**/.env.production)",
"Edit(**/.env.staging)",
"Edit(**/.env.test)",
"Edit(**/.envrc)",
"Edit(**/.env.*.local)",
"Read(**/*.pem)",
"Read(**/*.key)",
"Read(~/.ssh/**)",
"Read(~/.aws/**)",
"Read(~/.docker/**)",
"Read(~/.gnupg/**)",
"Read(~/.config/gcloud/**)",
"Read(~/.npmrc)",
"Read(~/.netrc)",
"Read(~/.git-credentials)",
"Read(~/.config/gh/hosts.yml)",
"Read(~/.pgpass)",
"Read(~/.pypirc)",
"Read(**/*.pfx)",
"Read(~/.kube/**)",
"Edit(**/*.pem)",
"Edit(**/*.key)",
"Edit(~/.ssh/**)",
"Edit(~/.aws/**)",
"Edit(~/.docker/**)",
"Edit(~/.gnupg/**)",
"Edit(~/.config/gcloud/**)",
"Edit(~/.npmrc)",
"Edit(~/.netrc)",
"Edit(~/.git-credentials)",
"Edit(~/.config/gh/hosts.yml)",
"Edit(~/.pgpass)",
"Edit(~/.pypirc)",
"Edit(**/*.pfx)",
"Edit(~/.kube/**)",
"Read(**/.ssh/**)",
"Read(**/.aws/**)",
"Read(**/.docker/**)",
"Read(**/.gnupg/**)",
"Read(**/.config/gcloud/**)",
"Read(**/.npmrc)",
"Read(**/.netrc)",
"Read(**/.git-credentials)",
"Read(**/.config/gh/hosts.yml)",
"Read(**/.pgpass)",
"Read(**/.pypirc)",
"Read(**/.kube/**)",
"Edit(**/.ssh/**)",
"Edit(**/.aws/**)",
"Edit(**/.docker/**)",
"Edit(**/.gnupg/**)",
"Edit(**/.config/gcloud/**)",
"Edit(**/.npmrc)",
"Edit(**/.netrc)",
"Edit(**/.git-credentials)",
"Edit(**/.config/gh/hosts.yml)",
"Edit(**/.pgpass)",
"Edit(**/.pypirc)",
"Edit(**/.kube/**)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Bash|PowerShell",
"hooks": [
{
"type": "command",
"command": "node"
},
{
"type": "command",
"command": "node"
}
]
}
]
}
} Skills (8)
Hooks (6)
| event | matcher | runs |
|---|---|---|
| PreToolUse | Bash|PowerShell | node |
| PreToolUse | Bash|PowerShell | node |
| PostToolUse | Edit | node |
| PostToolUse | Write | node |
| PostToolUse | Bash | node |
| Stop | * | node |
Permissions
deny (72)
Bash(*git commit*)
Bash(*git push*)
Read(**/.env)
Read(**/.env.local)
Read(**/.env.development)
Read(**/.env.production)
Read(**/.env.staging)
Read(**/.env.test)
Read(**/.envrc)
Read(**/.env.*.local)
Edit(**/.env)
Edit(**/.env.local)
Edit(**/.env.development)
Edit(**/.env.production)
Edit(**/.env.staging)
Edit(**/.env.test)
Edit(**/.envrc)
Edit(**/.env.*.local)
Read(**/*.pem)
Read(**/*.key)
Read(~/.ssh/**)
Read(~/.aws/**)
Read(~/.docker/**)
Read(~/.gnupg/**)
Read(~/.config/gcloud/**)
Read(~/.npmrc)
Read(~/.netrc)
Read(~/.git-credentials)
Read(~/.config/gh/hosts.yml)
Read(~/.pgpass)
Read(~/.pypirc)
Read(**/*.pfx)
Read(~/.kube/**)
Edit(**/*.pem)
Edit(**/*.key)
Edit(~/.ssh/**)
Edit(~/.aws/**)
Edit(~/.docker/**)
Edit(~/.gnupg/**)
Edit(~/.config/gcloud/**)
Edit(~/.npmrc)
Edit(~/.netrc)
Edit(~/.git-credentials)
Edit(~/.config/gh/hosts.yml)
Edit(~/.pgpass)
Edit(~/.pypirc)
Edit(**/*.pfx)
Edit(~/.kube/**)
Read(**/.ssh/**)
Read(**/.aws/**)
Read(**/.docker/**)
Read(**/.gnupg/**)
Read(**/.config/gcloud/**)
Read(**/.npmrc)
Read(**/.netrc)
Read(**/.git-credentials)
Read(**/.config/gh/hosts.yml)
Read(**/.pgpass)
Read(**/.pypirc)
Read(**/.kube/**)
ask (0)
—
allow (4)
Read(.env.example)
Read(**/.env.example)
Edit(.env.example)
Edit(**/.env.example)
Similar rigs
ruvnet/ruflo
🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native
Fort Knox 35.3k tok ·
Donchitos/Claude-Code-Game-Studios
Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.
Fort Knox 11.6k tok ·
FlorianBruniaux/claude-code-ultimate-guide
The most comprehensive Claude Code guide: agentic workflows, hooks, skills, MCP servers, quizzes, and production-ready templates. 430K+ lines.
Fort Knox 33.8k tok ·
trailofbits/claude-code-config
Opinionated defaults, documentation, and workflows for Claude Code at Trail of Bits
Fort Knox 0 tok ·