Skip to main content
subagent CX Codex

stellar-structure — Claude Code subagent: what it does, how to install

stellar-structure — a subagent for Claude Code that runs a code structure pass covering size, decomposition, and layer placement. Triggered by the stellar-review pipeline.

Apache-2.0 ★ 423 updated 2026-11-16

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/agents/stellar-structure.md
Open on GitHub

What stellar-structure does

The subagent evaluates code architecture against a mandate and checklist, returning findings in JSON format. Before review, it reads configuration files in .agents/skills/stellar-review/ and the assigned brief file.

File editing and shell command execution are explicitly denied in its permissions configuration. The final output is strictly a JSON document without conversational text or Markdown wrappers.

The agent runs exclusively as part of the review pipeline and should not be invoked directly for general prompts.

What it helps with

  • audit module decomposition and size
  • check layer placement and boundaries
  • generate findings in JSON schema format
  • execute architecture checks under ADR-0271

Example prompts for the agent

  • Run the structure pass using stellar-structure
  • Review module size and decomposition based on the brief
  • Perform layer placement check

How to install stellar-structure

Manually: put the files in place

.claude/agents/stellar-structure.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about stellar-structure

How to install stellar-structure in Claude Code?

Place the subagent file at .claude/agents/stellar-structure.md.

What does stellar-structure do?

Analyzes code size, decomposition, and layer organization against a provided brief, outputting a strict JSON findings report.

What are the permission rules for stellar-structure?

File editing and shell command execution are blocked, restricting the agent to read-only analysis.

Source text

stellar-structure.md · Apache-2.0
---
description: Stellar review — structure — size, decomposition, layer placement pass. Dispatched by the stellar-review pipeline with a pre-digested brief; never invoke directly for general questions.
mode: subagent
permissions:
  - action: edit
    resource: "*"
    effect: deny
  - action: shell
    resource: "*"
    effect: deny
---

You are a stellar-review **structure** pass agent (ADR-0271). The caller
dispatches you with one pre-digested brief file; your whole job is to
judge it and return findings as JSON.

Before reviewing, read these files (paths relative to the repository
root), in this order:

1. `.agents/skills/stellar-review/passes/structure.md` — your mandate
2. `.agents/skills/stellar-review/references/full-checklist.md` — doctrine
3. `.agents/skills/stellar-review/references/finding-schema.md` — output shape
4. `.agents/skills/stellar-review/references/severity-rubric.md` — severity rules

Then read the brief file the caller named (`.stellar/briefs/brief-structure[-N].md`)
fully. Its assigned units are your entire scope.

Rules:

- Report only findings inside your mandate, only on assigned units.
  Sealed units are decided — never report them, never re-report open or
  waived findings listed in the brief header.
- Be exhaustive within your mandate: every finding, with a verbatim quote
  and exact new-file line numbers. Never ration in your head — severity
  and nit-capping are the poster's job.
- You may open real files for context (callers, module layout) when the
  mandate calls for it, but findings anchor to in-scope units.
- Your final message is exactly one JSON document in the finding-schema
  shape — no prose, no markdown fences. Example:
  {"findings": [...], "resolutions": [...], "coverage": ["brief-structure.md"]}
  (include `resolutions` only when your brief has Resolution checks).

© relatedb · Apache-2.0 · relatedb/relate

Similar subagents

All subagents for Code review and refactoring →
folder-structure-blueprint-generator official github The folder-structure-blueprint-generator skill analyzes a project’s folders and creates a blueprint with tree views, naming rules, and file templates. Use it when a codebase needs a clear structure guide. CX Codex +1 9,438installs project-structure tartinerlabs project-structure audits directory layouts, flags file organisation anti-patterns, and safely moves code using git mv with automated import updates. CX Codex +1 521installs upgrade-stellar-contracts OpenZeppelin upgrade-stellar-contracts — a skill for upgrading Stellar/Soroban smart contracts with OpenZeppelin's upgradeable module. Use it to make contracts updatable, migrate storage data, or ensure compatibility across bytecode replacements. CX Codex +1 281installs Coding Structure with MVC and SOLID Principles Abdooo2235 Coding Structure with MVC and SOLID Principles instructs the AI to act as a software architect, explaining MVC architecture and SOLID principles with concrete code examples. GP ChatGPT ★ 178,201repo stars identify-page-structure adobe identify-page-structure splits a scraped webpage into sections and content sequences for AEM Edge Delivery Services import. Runs as a pipeline step, not by hand. CX Codex +1 1,600installs site-structure-optimizer aaron-he-zhu site-structure-optimizer — a skill that plans site structure and untangles internal linking: page hierarchy, URLs, hub clusters, orphan pages. It returns a structure score out of 100. CX Codex +1 1,500installs

From the same set18

The whole set →
relate This Claude Code skill guides Python work with Relate, an embedded openCypher graph database. It activates for building a local database, running Cypher queries, and handling query results. CX Codex +1 ★ 423repo stars relate This Claude Code skill guides JavaScript and TypeScript work with Relate, a local graph database queried with openCypher. It covers connections, transactions, and result handling. CX Codex +1 ★ 423repo stars rust-reviewer The rust-reviewer skill for Claude Code and Codex reviews Rust code for ownership, lifetimes, and error handling issues. It examines the whole project, including unsafe blocks and idiomatic Rust patterns. CX Codex +1 ★ 423repo stars agent-backlog-autopilot The agent-backlog-autopilot Claude Code skill takes one agent-backlog task from selection through a pull request. It pauses after the draft checks pass and waits for a human to mark the PR ready for review. CX Codex +1 ★ 423repo stars stellar-code-quality-review The stellar-code-quality-review Claude Code skill audits maintainability, abstraction quality, and file growth. Its staged review examines changes and related code units. CX Codex +1 ★ 423repo stars stellar-branching stellar-branching — a Claude Code subagent reviews branching growth and conditional logic. The stellar-review pipeline dispatches it with a prepared brief. CX Codex +1 ★ 423repo stars stellar-boundaries Claude Code subagent stellar-boundaries reviews boundaries, abstractions, and type contracts during a code review pipeline. CX Codex +1 ★ 423repo stars stellar-comparison stellar-comparison — a Claude Code subagent for comparison checks in the stellar-review pipeline. It receives a prepared brief and returns findings as JSON. CX Codex +1 ★ 423repo stars

Project sponsors

Companies that keep this analytics open