Monolith Review Orchestrator

Overview

Monolith-local Diversio PR review harness for deep PR understanding, deterministic worktree reuse/bootstrap, persistent review context across passes, resolved-comment-aware reassessment, backend monty-review handoff, and author-guiding review output.

This skill ships inside the Monolith Review Orchestrator plugin and can be installed through the Claude Code marketplace or directly in Codex from its skill path.

Parent Surface

Parent docs: Monolith Review Orchestrator

Related wrapper commands from the parent plugin:

When To Use This Skill

worktrees, submodules, PR context reads, reassessment passes, and GitHub posting step by step.

frontend/, optimo-frontend/, design-system/, or infrastructure/.

unresolved threads", "reassess after the author pushed updates", or "post the final review to GitHub".

local monolith state fresh.

This skill is an orchestrator. It does not replace repo-specific review taste.

available; fall back to gh only when needed.

reading and synthesis, but do not pretend there is a stable repo-specific review adapter unless one actually exists.

• The user wants an end-to-end PR review workflow instead of manually driving worktrees, submodules, PR context reads, reassessment passes, and GitHub posting step by step.
• The review spans one or more monolith submodules such as backend/, frontend/, optimo-frontend/, design-system/, or infrastructure/.
• The user says things like "deeply understand this PR", "check all comments and unresolved threads", "reassess after the author pushed updates", or "post the final review to GitHub".
• The user wants the agent to manage deterministic review worktrees and keep the local monolith state fresh.
• For Django4Lyfe/backend slices, invoke monty-code-review.
• For GitHub issue/PR metadata and comments, prefer the GitHub plugin/app when available; fall back to gh only when needed.
• For frontend or other non-backend slices, keep v1 narrower: do deep repo reading and synthesis, but do not pretend there is a stable repo-specific review adapter unless one actually exists.

Modes

Choose one mode early and state it explicitly to the user:

and report current status without doing a fresh full review.

before posting unless the user asked to post.

open concerns.

including inline comments only when the diff anchor is stable enough for the worker to validate safely.

If the prompt implies more than one mode, use this order:

status/review -> reassess if needed -> post

• Understand the PRs, read discussion history, audit unresolved comments, and report current status without doing a fresh full review.
• Do a full deep review, create/update local review artifacts, and stop before posting unless the user asked to post.
• Re-review after new commits, focusing on deltas, prior findings, and still open concerns.
• Draft the latest validated review for worker-owned GitHub publication, including inline comments only when the diff anchor is stable enough for the worker to validate safely.

V1 Scope

Treat this as a narrow v1 harness workflow, not a universal review brain.

Supported v1 scope:

and the worker publishes one top-level review plus zero or more inline comments atomically when the anchors validate cleanly

Explicitly out of scope for v1:

• single PR, or one explicitly linked cross-repo PR pair
• monolith-local execution only
• status, review, reassess, and worker-owned post mode
• deterministic worktree reuse/bootstrap
• persistent JSON-first review context plus markdown artifacts
• worker-owned final review publishing: Codex drafts, the worker revalidates, and the worker publishes one top-level review plus zero or more inline comments atomically when the anchors validate cleanly
• generic multi-PR batch posting
• generic unresolved-thread automation without a dedicated helper
• replies to existing review threads or partial inline publication
• repo-agnostic marketplace-style usage outside the Diversio monolith
• broad submodule branch normalization during review prep
• claiming reliable "final status" from comment lists alone

Prerequisites

This skill is monolith-local and should fail fast if these prerequisites are not met:

If preflight fails, stop and report the missing prerequisite instead of continuing heuristically.

Deterministic helpers for this skill now live under scripts/:

For the simple "what is each helper for?" explanation, load:

For the deep-understanding, comment-history, and author-guidance protocol, load:

• running inside a Diversio monolith checkout or sibling review worktree
• monolith scripts and docs are present
• uv, git, and git worktree are available
• GitHub auth is available if PR metadata or posting is requested
• the agent has permission to create sibling worktrees if bootstrap is needed
• scripts/preflight_review_env.py
• scripts/resolve_review_batch.py
• scripts/prepare_review_worktree.py
• scripts/fetch_review_threads.py
• scripts/review_state.py
• references/workflow-helpers.md
• references/review-context-protocol.md

Resources

Declared allowed tools:

Installation

Switch between Claude Code and Codex, then copy the install command for the runtime you use.

claude plugin marketplace add DiversioTeam/agent-skills-marketplace
claude plugin install monolith-review-orchestrator@diversiotech

CODEX_HOME="${CODEX_HOME:-$HOME/.codex}"
python3 "$CODEX_HOME/skills/.system/skill-installer/scripts/install-skill-from-github.py" \
  --repo DiversioTeam/agent-skills-marketplace \
  --path plugins/monolith-review-orchestrator/skills/monolith-review-orchestrator

Invocation:

/monolith-review-orchestrator:review-prs
/monolith-review-orchestrator:reassess-prs
/monolith-review-orchestrator:post-review

name: monolith-review-orchestrator