Code · Workflow

Claude Code only

Pure-CLI: scope, plan, write, fix all inside Claude Code

If you live in the terminal, you don't need a chat tab next to your editor. Claude Code can plan a change, edit the files, run the tests, and stage the commit — all in one session. CodeRabbit reviews the PR; you bounce findings back to the same Claude Code session for fixes.

· 5 months ago
CODEBUILDERINTERMEDIATEIntermediateFrom $0/mo
Claude CodeClaude CodeCodeRabbitCodeRabbit
The stack
Claude Code
Claude Code
Plan + write + fix

Give it the ticket, it produces a plan, asks clarifying questions, then implements. Skills encode your repo conventions; hooks gate dangerous commands. Subagents handle reviews and verifications without polluting the main thread.

Bundled with Claude Pro $20/mo · Max $100/mo · Ultra $200/mo · API meteredAlts: Codex, Cursor
CodeRabbit
CodeRabbit
Automated PR review

Same role as the recommended stack. The CLI-only loop pairs especially well with CodeRabbit because the agent can pipe `gh pr view` straight into its own context to fix findings without you copying anything.

Free for OSS · $30/mo per dev Essentials ($24 billed annually) · $60/mo Team · $90/mo AdvancedAlts: Claude
Real monthly cost
small
$0/mo
Solo OSS maintainer
  • claude-codeFree tier
  • coderabbitFree (OSS)
medium
$50/mo
Indie dev, daily PRs
  • claude-code$20 Pro
  • coderabbit$30/dev
heavy
$250/mo
Heavy agentic use, multiple parallel sessions
  • claude-code$100 Max
  • coderabbit$150 (5 devs)
Recent changes to this stack
Workflow
  1. 1
    Open a sessionClaude Code

    `cd repo && claude`. Hand it the ticket as the first message. Let it ask the clarifying questions a chat tab would have surfaced.

    Prompt · Plan-and-implement from a ticket (Claude Code)
    I want a small, well-scoped PR for the change below. Plan first, then implement. Ask 1 to 2 clarifying questions before you start writing if anything is genuinely ambiguous.

Ticket / problem:
"""
{{paste ticket}}
"""

Constraints:
- Smallest viable diff.
- Match the existing code style. Read 2 to 3 nearby files before introducing a new pattern.
- Run the project's test command before reporting done.
- If a CLAUDE.md or AGENTS.md exists at the repo root, treat it as authoritative for conventions.

When you're done: print the file list, the test result, and a 2-line summary I can paste as the commit message.
  2. 2
    Open the PRClaude Code

    Use Claude Code's `/pr` workflow (or `gh pr create`). It writes the PR description from the diff. CodeRabbit posts its review within ~60s.

  3. 3
    Triage CodeRabbit, in-sessionClaude Code

    Pipe the review into the same Claude Code session: `gh pr view --json comments | claude`. The agent sees the findings, the diff, and the codebase together — no copy-paste.

    Prompt · Triage and patch CodeRabbit findings inside Claude Code
    I just opened a PR. CodeRabbit posted comments. I'm pasting them below. For each comment:

1. Decide: real issue, style nit, or wrong (false positive).
2. For real issues + non-trivial nits: produce a minimal patch. Run the tests. Reply on the PR explaining the fix.
3. For false positives: write a 1-line PR reply explaining why we're declining, no code change.

Do NOT batch-resolve nits without reading them. Do NOT introduce changes outside the scope of each comment.

CodeRabbit comments:
"""
{{paste 'gh pr view --json comments' or the comment thread}}
"""
  4. 4
    Re-review and mergeCodeRabbit

    Push fixes; CodeRabbit re-reviews. Merge once it's quiet and the human review is approved.

Proof
Live app
aistack.sh — this site
aistack.sh

Built mostly inside Claude Code, terminal end-to-end. 28+ passes, 40+ PRs, the full SDLC inside one CLI session per ticket.

Repo
Source repo
github.com

AGENTS.md at the repo root encodes the conventions Claude Code reads on each session. Open it to see what 'authoritative repo conventions' looks like in practice.

PR
PR #29 · launch prep (sitemap + robots + 404 + error boundary)
github.com

Four loosely-related concerns shipped in one focused PR. Demonstrates the 'plan-and-implement in one CLI session' loop without a separate chat tab.

PR
PR #39 · slim /pricing under 2 MB Googlebot limit
github.com

Constrained, debug-flavored work — the kind of ticket that reads like 'figure out why X is too big and fix it'. Claude Code triaging and patching in the same session.

What it produced
Solo founder, comparison week

Ran the same 8 tickets through this stack and the chat-led recommended stack. Time-to-merge dropped from 90 to 55 min/PR average. The trade-off: 2 of the 8 tickets needed a chat-tab debate before the agent could plan well — for those, the chat-led stack still won.

Common pitfalls
No external rubber duck

When you genuinely don't know what to build, a CLI agent that's already implementing is the wrong tool. Drop back to a chat tab for the open-ended part, then come back to Claude Code to ship.

Yolo mode on a real repo

Claude Code can run shell commands. Configure permissions and hooks before you hand it a repo with deploy credentials, migrations, or a production .env in scope.

Other ways to do Ship code with AI
Ship code with AI Recommended
Plan in Claude chat, write in Claude Code, review with CodeRabbit
$0/mo
Claude CodeCodeRabbit
View stack
Antigravity (Google)
Google's AI IDE: Gemini 2M-context inside the editor
$0/mo
Antigravity
View stack
Codex (CLI + cloud)
OpenAI Codex: terminal CLI for active work, cloud lane for autonomous PRs
$0/mo
Codex
View stack
Cursor (IDE-first)
AI inside the editor, not in a chat tab or terminal
$0/mo
View stack
Windsurf (Devin Local)
Cognition's IDE with the Devin Local autonomous-edit agent
$0/mo
Windsurf
View stack
Weekly changelog

What changed in AI tools and the stacks that ship. One email a week.

Spotted something off?
Wrong price, dead link, stale tool — anything. We review every fix.
Suggest a fix to this stack