~ / rigs / pruthvidarji1993 / ai-automation-jira

pruthvidarji1993/ai-automation-jira

AI-assisted dev workflow: Jira ticket in, reviewed PR out. Claude Code plugin + GitHub Copilot prompts with human approval gates (plan, diff).

↗ GitHub ★ 0 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
~2.0k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
3/5
Blocks destructive commands · Pre-tool screening hook · No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit pruthvidarji1993/ai-automation-jira/.claude ./rig-ai-automation-jira  # 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 pruthvidarji1993/ai-automation-jira/.claude/skills/debug .claude/skills/debug
$ npx degit pruthvidarji1993/ai-automation-jira/.claude/skills/feature .claude/skills/feature
$ npx degit pruthvidarji1993/ai-automation-jira/.claude/skills/implement .claude/skills/implement
$ npx degit pruthvidarji1993/ai-automation-jira/.claude/skills/intake .claude/skills/intake
$ npx degit pruthvidarji1993/ai-automation-jira/.claude/skills/plan .claude/skills/plan
$ npx degit pruthvidarji1993/ai-automation-jira/.claude/skills/refactor .claude/skills/refactor
$ npx degit pruthvidarji1993/ai-automation-jira/.claude/skills/research .claude/skills/research
$ npx degit pruthvidarji1993/ai-automation-jira/.claude/skills/review .claude/skills/review
$ npx degit pruthvidarji1993/ai-automation-jira/.claude/skills/ship .claude/skills/ship
$ curl -fsSL --create-dirs -o .claude/agents/lead.md https://raw.githubusercontent.com/pruthvidarji1993/ai-automation-jira/main/.claude/agents/lead.md
$ curl -fsSL --create-dirs -o .claude/agents/reviewer-deep.md https://raw.githubusercontent.com/pruthvidarji1993/ai-automation-jira/main/.claude/agents/reviewer-deep.md
$ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/pruthvidarji1993/ai-automation-jira/main/.claude/agents/reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/scout.md https://raw.githubusercontent.com/pruthvidarji1993/ai-automation-jira/main/.claude/agents/scout.md

Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash|Edit|Write|NotebookEdit|MultiEdit",
        "hooks": [
          {
            "type": "command",
            "command": "node \"$CLAUDE_PROJECT_DIR\"/plugins/dev-workflow/hooks/restrict-protected-push.mjs"
          }
        ]
      }
    ]
  }
}

Skills (9)

Subagents (4)

lead
model: opus
Judgment lead for the dev-workflow steps where a wrong call is expensive - root-cause analysis on a bug, and the final verification of every review finding. Started by the feature, research and review
reviewer-deep
model: opus
Fresh-context reviewer for one dimension of a diff on high-risk work - security, permissions, money or contracts, data writes or deletes, auth, migrations, production incidents. Started by the review
reviewer
model: sonnet
Fresh-context reviewer for one dimension of a diff (correctness, error handling, conventions, tests, types, readability) on normal-risk work. Started by the review and ship skills; returns findings wi
scout
model: sonnet
Narrow read-only lookup in the codebase - confirm or rule out one layer (data fetching, permissions, config or flags, an API contract, a shared component) or answer one factual question, with file:lin

Hooks (1)

eventmatcherruns
PreToolUseBash|Edit|Write|NotebookEdit|MultiEditnode "$CLAUDE_PROJECT_DIR"/plugins/dev-workflow/hooks/restrict-protected-push.mjs

Similar rigs

copied ✓