Thakurvaibhav/platform-agent-harness
Portable behavioral specification and coordination protocol for AI coding agents doing Kubernetes, Helm, ArgoCD, CI, and observability work.
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 Thakurvaibhav/platform-agent-harness/skills ./rig-platform-agent-harness/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 Thakurvaibhav/platform-agent-harness/skills/adopt-eval .claude/skills/adopt-eval $ npx degit Thakurvaibhav/platform-agent-harness/skills/contract-validation .claude/skills/contract-validation $ npx degit Thakurvaibhav/platform-agent-harness/skills/create-pr .claude/skills/create-pr $ npx degit Thakurvaibhav/platform-agent-harness/skills/design .claude/skills/design $ npx degit Thakurvaibhav/platform-agent-harness/skills/graphify .claude/skills/graphify $ npx degit Thakurvaibhav/platform-agent-harness/skills/helm-upgrade .claude/skills/helm-upgrade $ npx degit Thakurvaibhav/platform-agent-harness/skills/ingest-reading .claude/skills/ingest-reading $ npx degit Thakurvaibhav/platform-agent-harness/skills/k8s-debug .claude/skills/k8s-debug $ npx degit Thakurvaibhav/platform-agent-harness/skills/parallax-review .claude/skills/parallax-review $ npx degit Thakurvaibhav/platform-agent-harness/skills/shiny-engineer .claude/skills/shiny-engineer $ npx degit Thakurvaibhav/platform-agent-harness/skills/stakeholder-comms .claude/skills/stakeholder-comms $ npx degit Thakurvaibhav/platform-agent-harness/skills/stop-slop-code .claude/skills/stop-slop-code $ npx degit Thakurvaibhav/platform-agent-harness/skills/systematic-debugging .claude/skills/systematic-debugging $ npx degit Thakurvaibhav/platform-agent-harness/skills/upstream-triage .claude/skills/upstream-triage $ npx degit Thakurvaibhav/platform-agent-harness/skills/verify-claims .claude/skills/verify-claims
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 (15)
Similar rigs
Adityaraj0421/naksha-studio
A virtual design team for Claude Code, Cursor, Windsurf, Gemini CLI, and Copilot — 26 roles, 62 commands, 15,000+ lines of expert design knowledge. Your agency's design brain, inside your terminal.
Minimalist 2.4k tok ·
rileyhilliard/claude-essentials
—
Skill Collector 4.4k tok ·
mjacobus/dotfiles
My .dotfiles
Minimalist 142 tok ·
itslab42/agentctl
Define AI coding-agent permissions once, enforce them everywhere. One .ai/ source of truth compiles to native configs for Claude Code, Codex, OpenCode, Cursor & Kiro
Minimalist 1.2k tok ·