mrkeyoor.comAsk

donvito/codex-astra-luna-orchestratortested 29 Sept 2026commit 30b7d0b

codex-astra-luna-orchestrator review

Consider this bundle if you already use Codex and want reusable role configurations for work that benefits from separation.

  • Install 21 s
  • Build 8 s
9/9tests passed
  • 35 packages
LLM Toolsevaluationupdated 25 Oct 2026
-1stars / 7d

Codex Astra Luna Orchestrator packages project configuration, custom agent roles, and an orchestration skill for Codex. Its six profiles assign a root agent, Luna execution roles, and a separate reviewer. It is a configuration bundle for an existing Codex installation; our recorded setup steps do not establish that Codex itself was installed or that a delegated coding task worked.

Verdict

Consider this bundle if you already use Codex and want reusable role configurations for work that benefits from separation. Our September 29, 2026 run at commit 30b7d0b recorded successful harness steps and passing pytest output, but did not validate an installed Codex binary, live model routing, coding quality, speed, or token savings. Start with a disposable target repository, inspect the copied instructions, and compare a suitable task with your existing workflow before adopting it across projects.

We ran it

Lab card: what happened when we ran codex-astra-luna-orchestrator
Lab card from our sandbox run
Screenshot of codex-astra-luna-orchestrator (github.com/donvito/codex-astra-luna-orchestrator)
github.com/donvito/codex-astra-luna-orchestrator
Install✓ · 21s35 packages · 37 MB
Build✓ · 8s
Tests✓ · 9s9 passed · 0 failed of 9 (pytest)
Known vulns0(pip-audit)
Repo58 files~871 lines of source · 0.2 MB · 0 CI workflows · tests dir

Answers from our run

Does codex-astra-luna-orchestrator build from source?

Dependencies installed in 21 seconds (35 packages), and the build succeeded in 8 seconds. We cloned commit 30b7d0b into a clean Debian container with 3 CPUs and no project-specific setup.

Do codex-astra-luna-orchestrator's tests pass?

Yes. The project's own test command finished in 9 seconds and reported 9 passed, 0 failed (pytest).

Does codex-astra-luna-orchestrator have known vulnerabilities in its dependencies?

pip-audit found none in the dependency tree at the time of our run.

Who should not use codex-astra-luna-orchestrator?

Developers seeking demonstrated token savings or faster coding: our recorded run measured neither.

What are the alternatives to codex-astra-luna-orchestrator?

Codex, Superpowers. Consider this bundle if you already use Codex and want reusable role configurations for work that benefits from separation.

Setup3/5The README documents target selection, component confirmation, and preservation of existing instructions. Our dated run does not establish interactive profile installation, an installed Codex binary, or model access.
Docs3/5The README describes six profiles, role assignments, installed paths, and project/global setup. Live compatibility and model routing were not validated.
Community2/5Issues 5 and 11 provide concrete user reports. The supplied evidence does not establish broad adoption or support responsiveness; star counts are not used as quality evidence.
Maturity2/5Release v0.2.1 and our September 29, 2026 pytest output provide limited validation. No CI workflow was detected in the reviewed checkout, and no orchestration workload was measured.

Who it’s for

Codex users handling work that can be divided into independent assignments.
Developers who want project-scoped explorer, worker, tester, researcher, and reviewer configurations.
Teams willing to review the installed instructions, confirm access to each configured model, and measure their own task outcomes.

Who it’s NOT for

Developers seeking demonstrated token savings or faster coding: our recorded run measured neither.
Teams expecting every small task to benefit from delegation. Issue 5 reports increased context use and occasional slowdowns from eager delegation.
Users expecting a profile install to grant model access or immediately change an existing conversation.
Repositories where changes to .codex, .agents, or AGENTS.md cannot be reviewed and accepted.

Setup reality

In our recorded run on September 29, 2026, at commit 30b7d0bb7e9b3b9a7d27e78a11c468f95c4cf704, the install step exited successfully in 21.428 seconds, the build-labelled step in 8.245 seconds, and the test step in 9.371 seconds. The stored dependency summary records 35 packages and 37 MB. The install tail identifies a Python 3.12.12 environment; it does not show a Codex installation or a completed interactive profile installation.

The test output reports 9 passed and 23 subtests passed in 0.61 seconds. That is pytest's reported execution time, distinct from the harness test-step duration. The stored parser summary records 9 passed, 0 failed, 0 skipped, and 0 errors, but exhaustive unique coverage was not verified. The full harness duration is recorded as 55 seconds.

The pip-audit record reports zero advisories. Audit coverage is unknown, so this does not establish dependency safety.

According to the README, the shell and PowerShell installers target an existing repository, ask which profile and components to install, require confirmation before updating existing component files, and preserve existing AGENTS.md content. These are documented installer behaviors, not observations from our run.

Decide whether the work needs separate agents

Codex Astra Luna Orchestrator supplies a ready-made division of work. The decision is whether your tasks benefit from that division enough to justify additional agent activity.

Issue 5 describes a user's experience on a production Laravel codebase: relatively simple tasks expanded into explorer, worker, tester/reviewer, and orchestrator cycles. The reporter says this increased context use and occasionally slowed straightforward work. This is a user report, not our benchmark or proof that every profile behaves that way.

Official Codex documentation explains the tradeoff: each subagent performs its own model and tool work, so comparable subagent workflows consume more tokens than single-agent runs. Independent exploration can benefit from parallel work; simultaneous edits can create conflicts and coordination overhead. Use that distinction when deciding which assignments deserve separate agents.

Six profiles, with a dated model distinction

The README at reviewed commit 30b7d0b lists six profiles. Pro uses GPT-6 Astra at medium effort as root, GPT-6 Luna at max effort for execution, and Astra at low effort for review. Plus uses Luna at max effort as root, Luna at medium effort for execution, and Astra at low effort for review. Both have four-subagent and two-subagent variants.

The two Sol profiles at that commit use GPT-6 Sol at max or medium effort for root and reviewer, with Luna at max effort for execution and a four-subagent cap. The supplied current README instead specifies GPT-6.1 Sol for the Sol orchestrator and reviewer. The profile directory names remain GPT6-SolMax-LunaMax and GPT6-SolMedium-LunaMax. Our recorded run does not validate that later configuration.

Release v0.2.1 describes the original four Pro/Plus profiles moving their Luna pins from GPT-5.6 to GPT-6 while retaining their reasoning levels and subagent limits. Its statement that all nine tests passed is the maintainer's release verification, separate from our stored run.

What our recorded run establishes

Our run is dated September 29, 2026, at commit 30b7d0bb7e9b3b9a7d27e78a11c468f95c4cf704. The stored sandbox configuration specifies 3 CPUs, 8 GB of memory, and image ghcr.io/astral-sh/uv:python3.12-bookworm. The install tail identifies Python 3.12.12.

Recorded stage Observation Limit
Install Exit 0 in 21.428 seconds; dependency summary records 35 packages and 37 MB The available tail only identifies the Python environment; it does not establish a Codex or profile installation
Build-labelled step Exit 0 in 8.245 seconds Its tail is empty, so the record does not establish what was built
Test Exit 0 in 9.371 seconds; output reports 9 passed and 23 subtests passed in 0.61 seconds Parser summaries do not establish exhaustive unique coverage
Audit pip-audit records zero advisories Coverage is unknown; zero advisories is not proof of safety

The stored harness total is 55 seconds. The rounded install, build, and test durations sum to 38 seconds, but that sum is neither installation time nor the complete run duration.

The checkout summary records 58 files, approximately 871 lines of source, 0.2 MB, a tests directory, no detected CI workflows, and no Dockerfile. These are observations about that checkout. We did not run a delegated coding workload, verify installed-binary behavior, measure model access, or compare cost and task quality.

Review the project changes before installing

The README directs users to clone this repository, run setup.sh or setup.ps1, select an existing target repository other than the installer repository, and choose a profile. It says the installer copies configuration into .codex/, the skill into .agents/, and project instructions into AGENTS.md. Existing component files require confirmation before updates; existing AGENTS.md content is preserved, with instructions appended when that file exists.

Codex loads project configuration only for trusted projects. Project configuration takes precedence over user defaults, while higher-priority overrides and managed requirements still apply. Inspect the selected model settings, concurrency, project permissions, and instructions before accepting those changes.

Custom agent instructions do not create an independent security boundary. Current official documentation says custom agents inherit the parent's permissions, provider, and MCP servers; placing sandbox or approval settings in a custom agent file does not override the parent configuration.

The README also describes global installation and tells users to merge settings rather than overwrite existing Codex configuration. A project-scoped trial gives you a smaller set of changes to inspect first.

Confirm the models in a new session

Profile names do not establish account entitlements. Confirm that your client and account can use every configured model. Issue 11 reports that initial model selection appeared in new conversations but not existing conversations or branches. Treat this as a reported limitation, not a universal compatibility result.

Install into a disposable target repository, inspect the resulting files, start a new Codex session, and check the selected roles. Then compare an independently divisible task with your existing workflow. Record task completion, review findings, elapsed time, and token use separately. Our run supplies no savings benchmark for either the reviewed or current profiles.

How the ratings work

These are editorial ratings of the supplied evidence, not measured performance scores. On the five-point scale, 1 means substantial obstacles or very little support, 2 means partial support with major unknowns, 3 means a documented basis with meaningful validation limits, 4 means strong support with bounded gaps, and 5 requires broad corroboration relevant to the category. Missing adoption, compatibility, or workload evidence earns no positive credit.

Setup receives 3/5 because the documented installation path includes confirmation and preservation steps, but our run does not validate interactive installation or model access. Documentation receives 3/5 because the README explains profile assignments and installed paths, while live compatibility remains untested. Community receives 2/5 because the supplied issues contain concrete user feedback but do not establish adoption or support responsiveness. Maturity receives 2/5 because v0.2.1 and local test output provide some validation, while the reviewed checkout has no detected CI workflow and no measured orchestration workload.

Alternatives

ProjectWhat it isPick it when
Codex gh↗Codex supports custom agents and subagent workflows directly.Choose direct Codex configuration when you want to define a few roles and control delegation without adopting this bundle's profiles and skill.
Superpowers gh↗A skills-based development methodology covering design, planning, implementation, testing, and review.Choose Superpowers when you want a broader development process rather than a set of Codex model-routing profiles. Its README describes both subagent-driven and inline execution paths.

What people are saying

  1. [velocity-scout] donvito/codex-astra-luna-orchestrator

Sources

  1. Codex Astra Luna Orchestrator README
  2. Codex Astra Luna Orchestrator v0.2.1
  3. Real project delegation feedback
  4. Model selection conversation issue
  5. Official OpenAI Codex subagent documentation
  6. Official OpenAI Codex configuration basics

More llm tools reviews