~ / rigs / kkunan / agentic-delivery

kkunan/agentic-delivery

Claude Code plugin: approve one plan, and agents build, review, test, and ship the feature.

↗ GitHub ★ 0 MIT updated today 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
~478 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 kkunan/agentic-delivery/agents ./rig-agentic-delivery/agents
$ npx degit kkunan/agentic-delivery/commands ./rig-agentic-delivery/commands
$ npx degit kkunan/agentic-delivery/skills ./rig-agentic-delivery/skills
$ npx degit kkunan/agentic-delivery/hooks ./rig-agentic-delivery/hooks

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 kkunan/agentic-delivery/skills/controller .claude/skills/controller
$ npx degit kkunan/agentic-delivery/skills/platform-flutter .claude/skills/platform-flutter
$ npx degit kkunan/agentic-delivery/skills/platform-go .claude/skills/platform-go
$ npx degit kkunan/agentic-delivery/skills/platform-ios .claude/skills/platform-ios
$ npx degit kkunan/agentic-delivery/skills/product-owner .claude/skills/product-owner
$ npx degit kkunan/agentic-delivery/skills/run-rules .claude/skills/run-rules
$ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/kkunan/agentic-delivery/main/agents/implementer.md
$ curl -fsSL --create-dirs -o .claude/agents/qa-reviewer.md https://raw.githubusercontent.com/kkunan/agentic-delivery/main/agents/qa-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/kkunan/agentic-delivery/main/agents/reviewer.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 (6)

Subagents (3)

implementer
model: sonnet
Senior engineer for implementing one task from a plan brief. Use for every coding task that the spec-driven pipeline dispatches.
qa-reviewer
model: opus
Read-only QA lead who reviews a spec or plan for testability before any code exists. Use as the QA seat at the spec review, and whenever the manual checks of a plan need judging.
reviewer
model: opus
Read-only tech lead who reviews the diff of one task against its brief. Use after every implementer task and before any branch is offered for review.

Slash commands (1)

/feature

Similar rigs

copied ✓