cd /news/ai-agents/agents-concerto-orchestrating-claude… · home topics ai-agents article
[ARTICLE · art-74366] src=promptcube3.com ↗ pub= topic=ai-agents verified=true sentiment=· neutral

Agents-Concerto: Orchestrating Claude Code for PRs

Developer moruno21 released agents-concerto, an orchestration layer for Claude Code that enforces a four-role agent pipeline to generate pull requests without auto-merge. The system uses a Given-When-Then format for acceptance criteria, worktree isolation, and a two-party authority rule to keep final human control over merges. The open-source code is available at github.com/moruno21/agents-concerto.

read2 min views1 publishedJul 26, 2026
Agents-Concerto: Orchestrating Claude Code for PRs
Image: Promptcube3 (auto-discovered)

To fix this, I built agents-concerto. It isn't a standalone app, but an orchestration layer for Claude Code. Think of it as a conductor and a set of players; the conductor manages the flow but never touches an instrument, ensuring the final merge always stays in human hands.

The system relies on a strict set of constraints to maintain quality:

Two-party authority: No agent that writes code is allowed to approve or merge it.Worktree isolation: Every agent operates in its own git worktree to avoid messing up the local checkout.No auto-merge: The process stops exactly at "PR ready."Model by complexity: The model isn't tied to a role; it's picked based on the complexity tier of the task.

The Logic of Acceptance Criteria #

The biggest shift in my AI workflow was treating acceptance criteria as test specs rather than human notes. Using a Given-When-Then format (Given X

, when Y

, then Z

), the system ensures that every requirement has an observable result.

This criterion travels through the pipeline: it's defined during the shaping phase, converted into a test during implementation, and verified by the reviewer. Because the "then" must be observable, it prevents the AI from cheating by asserting on internal state.

The Agent Pipeline #

I've divided the labor across four distinct roles:

Orchestrator (Opus): Handles decomposition and dispatching. It is strictly forbidden from writing application code.Classifier (Sonnet): A read-only agent that assigns a complexity tier (complex

vsstandard

) to determine which model handles the task.Implementer: This agent uses a "Tidy First" approach—it submits a structural refactor commit first, then a separate behavioral commit. It never mixes the two.Reviewer (Opus): Limited toRead

,Grep

,Glob

, andBash

. It has noWrite

orEdit

permissions, meaning it can describe a fix but cannot apply it.

By forcing "outside-in" testing—asserting only on outputs, UI, or API responses—we've eliminated the "green tests, zero confidence" problem.

For those looking for a real-world LLM agent deployment, the full logic is available here:https://github.com/moruno21/agents-concerto

Next AI Agents for Regulated Industries: My Workflow →

── more in #ai-agents 4 stories · sorted by recency
── more on @moruno21 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/agents-concerto-orch…] indexed:0 read:2min 2026-07-26 ·