Agent skill

Astra Orchestrator

by donvito in donvito/codex-astra-luna-orchestrator

Orchestrate complex Codex coding work with GPT-6.1 Sol at medium reasoning as planner/integrator and reviewer and GPT-6 Luna at max reasoning for exploration, implementation, testing, and research.

Apache-2.0Auto-check passedDevelopment

Install Astra Orchestrator

skills CLI
$ npx skills add donvito/codex-astra-luna-orchestrator --skill astra-orchestrator -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install donvito/codex-astra-luna-orchestrator astra-orchestrator --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/donvito/codex-astra-luna-orchestrator.git skills-src && mkdir -p .claude/skills && cp -r skills-src/profiles/GPT6-SolMedium-LunaMax/agents/skills/astra-orchestrator .claude/skills/astra-orchestrator && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
astra-orchestrator
GitHub stars
1.7k
Token cost
~597 tokens
SKILL.md length
258 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
Apache-2.0

At a glance

Orchestrate complex Codex coding work with GPT-6.1 Sol at medium reasoning as planner/integrator and reviewer and GPT-6 Luna at max reasoning for exploration, implementation, testing, and research.

  • Multi-file features
  • SKILL.md covers Topology, Delegation and Verification
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Debugging across components

What it does

Astra Orchestrator is an agent skill from donvito/codex-astra-luna-orchestrator. Orchestrate complex Codex coding work with GPT-6.1 Sol at medium reasoning as planner/integrator and reviewer and GPT-6 Luna at max reasoning for exploration, implementation, testing, and research. Use for multi-file features, debugging across components, repo-wide changes, parallelizable workstreams, or when the user asks to delegate. Do not use for trivial edits or simple questions.

Its SKILL.md is about 600 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development. The repository describes itself as: Use Astra or Sol as orchestrator and Luna for subagents in Codex. The licence is Apache-2.0.

When your agent uses it

  • Multi-file features
  • Debugging across components
  • Repo-wide changes
  • Parallelizable workstreams

Example prompts

  • “/astra-orchestrator”

What it can do on your machine

Read from SKILL.md and the folder at commit f5efba0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Astra Orchestrator loads about 597 tokens when it runs. Until then it costs about 102 tokens; SKILL.md has 258 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~102
When it runs · the whole SKILL.md, loaded when a task matches
~597

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from donvito/codex-astra-luna-orchestrator at commit f5efba0, republished under its Apache-2.0 licence (© donvito). 258 words, ~597 tokens.

Download SKILL.mdSave it as .claude/skills/astra-orchestrator/SKILL.md (or your agent's skills folder).
name
astra-orchestrator
description
Orchestrate complex Codex coding work with GPT-6.1 Sol at medium reasoning as planner/integrator and reviewer and GPT-6 Luna at max reasoning for exploration, implementation, testing, and research. Use for multi-file features, debugging across components, repo-wide changes, parallelizable workstreams, or when the user asks to delegate. Do not use for trivial edits or simple questions.

Orchestrator — GPT-6.1 Sol Medium + GPT-6 Luna Max

The user's explicit instructions take precedence over this skill.

Topology

  • root: gpt-6.1-sol at medium reasoning
  • explorer, worker, tester, researcher: gpt-6-luna at max reasoning
  • reviewer: gpt-6.1-sol at medium reasoning, in an independent read-only context

The role files in .codex/agents/ pin these models and reasoning levels; generic subagents inherit the Luna defaults in .codex/config.toml. Do not change the root model from within a session.

Delegation

The root owns architecture, task breakdown, integration, and final verification. Keep genuinely small tasks root-only. For work spanning multiple files, independent workstreams, cross-component debugging, or useful independent review, delegate bounded tasks to specialized agents when available. If required delegation is unavailable, report that rather than claiming it happened.

For each delegated task, specify the objective, scope, context, constraints, deliverable, and acceptance criteria. When spawning, select the named role and its pinned model; do not silently replace a Luna worker with the root. Use explorer for mapping code, worker for implementation, tester for verification, researcher for version-specific facts, and reviewer for independent post-change review. Do not let multiple workers edit the same files without explicit ownership boundaries.

Run independent tasks in parallel and serialize dependent work. Prefer exploration, architecture decision, bounded implementation, targeted testing, independent review when useful, then integration and final verification. Do not spawn every role mechanically. Report agent failures and resolve material findings before finishing.

Verification

Inspect the final diff, verify requested behavior, run relevant tests, and state any validation that could not be performed. Never claim a subagent was used unless it was actually spawned.

© donvito, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in profiles/GPT6-SolMedium-LunaMax/agents/skills/astra-orchestrator of donvito/codex-astra-luna-orchestrator.

Open the folder on GitHubat commit f5efba0

Compare with similar skills

Astra Orchestrator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Astra Orchestrator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Astra Orchestrator this skilldonvito/codex-astra-luna-orchestrator1.7k—~597Automated safety check: PassApache-2.0
Trellis Session Insightmindfold-ai/Trellis15k4 repos~1.7kAutomated safety check: PassAGPL-3.0
Warp Factory Fileswarpdotdev/warp65k1 repos~2.5kAutomated safety check: PassAGPL-3.0
Migrate Core Code to Submodulestinyhumansai/openhuman42k—~2.6kAutomated safety check: PassGPL-3.0
Analyze Logsactivepieces/activepieces25k1 repos~1.6kAutomated safety check: PassMIT
GitHub Review Iterationprisma/orm48k—~2.2kAutomated safety check: PassApache-2.0

Similar skills

  • Trellis Session Insight

    mindfold-ai/Trellis

    Reach into past AI conversation history through the trellis mem CLI.

    15k GitHub starsUsed in 4 repos~1.7k tokens
    DevelopmentAuto-check passed
  • Warp Factory Files

    warpdotdev/warp

    Authors and edits file-based Warp software factory definitions rooted at factory.yaml, covering agents, automations, scorers and webhooks, and validates them before a pull request.

    65k GitHub starsUsed in 1 repo~2.5k tokens
    DevelopmentAuto-check passed
  • Migrate Core Code to Submodules

    tinyhumansai/openhuman

    Plans and carries out moving non-host-specific code and its tests from the OpenHuman core into vendored tiny submodule libraries, then releases the submodule and re-pins the host.

    42k GitHub stars~2.6k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Analyze Logs

    activepieces/activepieces

    Analyze application logs from the .evlog/logs/ directory. An agent skill from activepieces/activepieces.

    25k GitHub starsUsed in 1 repo~1.6k tokens
    DevelopmentAuto-check passed
  • Official

    Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.

    48k GitHub stars~2.2k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Release

    PrefectHQ/fastmcp

    Cut a FastMCP release end to end. An agent skill from PrefectHQ/fastmcp.

    28k GitHub stars~2.9k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from donvito/codex-astra-luna-orchestrator

  • Astra Orchestrator

    donvito/codex-astra-luna-orchestrator

    Orchestrate complex Codex coding work with GPT-6.1 Sol at max reasoning as planner/integrator and reviewer and GPT-6 Luna at max reasoning for exploration, implementation, testing, and research.

    1.7k GitHub stars~594 tokensUpdated 9 days ago
    Auto-check passed
  • Astra Orchestrator

    donvito/codex-astra-luna-orchestrator

    Orchestrate complex Codex coding work for the Plus profile with GPT-6 Luna at max reasoning as planner/integrator, Luna subagents for exploration, implementation, testing, and research, and an Astra…

    1.7k GitHub stars~3k tokensUpdated 9 days ago
    Auto-check passed
  • Astra Orchestrator

    donvito/codex-astra-luna-orchestrator

    Orchestrate complex Codex coding work for the Pro profile with GPT-6 Astra at medium reasoning as planner/integrator, Luna subagents for exploration, implementation, testing, and research, and an…

    1.7k GitHub stars~3.1k tokensUpdated 9 days ago
    Auto-check passed

Questions about Astra Orchestrator

What does Astra Orchestrator do?

Orchestrate complex Codex coding work with GPT-6.1 Sol at medium reasoning as planner/integrator and reviewer and GPT-6 Luna at max reasoning for exploration, implementation, testing, and research. Astra Orchestrator is an agent skill from donvito/codex-astra-luna-orchestrator.1 Sol at medium reasoning as planner/integrator and reviewer and GPT-6 Luna at max reasoning for exploration, implementation, testing, and research.

When should I use Astra Orchestrator?

Astra Orchestrator fits situations like: multi-file features; debugging across components; repo-wide changes; parallelizable workstreams.

How do I install Astra Orchestrator in Claude Code?

Run `npx skills add donvito/codex-astra-luna-orchestrator --skill astra-orchestrator -a claude-code`. Or copy the skill folder (profiles/GPT6-SolMedium-LunaMax/agents/skills/astra-orchestrator in donvito/codex-astra-luna-orchestrator) into .claude/skills/astra-orchestrator in your project. Claude Code loads it when a task matches its description.

How do I install Astra Orchestrator in Codex?

Run `npx skills add donvito/codex-astra-luna-orchestrator --skill astra-orchestrator -a codex`. Or copy the skill folder (profiles/GPT6-SolMedium-LunaMax/agents/skills/astra-orchestrator in donvito/codex-astra-luna-orchestrator) into .agents/skills/astra-orchestrator in your project. Codex loads it when a task matches its description.

Can I use Astra Orchestrator in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add donvito/codex-astra-luna-orchestrator --skill astra-orchestrator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/astra-orchestrator, .gemini/skills/astra-orchestrator, .github/skills/astra-orchestrator and .opencode/skills/astra-orchestrator in your project.

What does Astra Orchestrator need to run?

SKILL.md names no scripts, command-line tools or credentials: Astra Orchestrator is instructions for the agent only.

Does Astra Orchestrator access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Astra Orchestrator safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Astra Orchestrator use?

Astra Orchestrator is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Astra Orchestrator use?

About 597 tokens (SKILL.md is roughly 2.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Astra Orchestrator?

Skills that share tags, products or a category with Astra Orchestrator: Trellis Session Insight (mindfold-ai/Trellis, 15k stars), Warp Factory Files (warpdotdev/warp, 65k stars), Migrate Core Code to Submodules (tinyhumansai/openhuman, 42k stars) and Analyze Logs (activepieces/activepieces, 25k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Astra Orchestrator?

donvito (a GitHub user) maintains it in donvito/codex-astra-luna-orchestrator, which has 1,696 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 1, 2026.

Source: donvito/codex-astra-luna-orchestrator on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.