agentpluginsdirectory
phni3j9a avatar

axiom

v0.1.9

by phni3j9a

Codex engineering with Astra XHIGH planning and advice, Luna MAX Fast workers, Sol MAX design, independent Sol review, and context isolation.

What axiom does, in the publisher's words

Axiom is a guidance-first Codex plugin for non-trivial software engineering.

> Main thinks. Astra designs. Luna executes. Sol reviews. > > Main context is expensive; Luna compute is almost free.

  • Main (Sol or Astra) owns intent, architecture, design direction and constraints, integration, and acceptance.
  • The recommended environment is Codex v0.147 or later, including v0.153. Main may use gpt-5.6-sol with xhigh recommended, or gpt-6-astra with Main reasoning effort following the user's or session's setting; this is separate from the design worker's fixed MAX effort.
  • Axiom v0.1.9 preserves the v0.1.4 economics principle that ordinary Luna MAX worker usage is treated as almost free for orchestration decisions.
  • Direct-spawn Luna MAX performs bounded exploration and implementation; useful spawns should not be suppressed merely to conserve Luna usage.

From the project README, punctuation lightly normalized · Open the README on GitHub

Skills
1
MCP servers
0
Stars
0
License
MIT
Repo created
2026-08-17
Last pushed
2026-09-13
Publisher type
User
Version
0.1.9

Links

Skills · 1

axiom
Apply proactively to non-trivial software engineering work, feature implementation, bug fixes, refactoring, debugging, testing, codebase investigation, interface design, and code review, when delegation, context isolation, independent review, or Git coordination can improve delivery. Keep intent, arc…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

Category

Agent Tooling. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.

Keywords

codex · multi-agent · delegation · context-isolation · luna · sol · design · review · git · parallelism · astra · advisor · planning

Related by publisher and keywords

  • maestraphni3j9a

    Explicitly activated, context-isolated multi-agent execution with Main-owned planning and bounded review.

  • luna-factoryjoshyorko

    Luna-first orchestration for economical delegation, bounded escalation, and evidence-backed completion.

  • dialecticslior

    Configuration-first multi-agent design debate. Agents with different roles (architect, security, performance, simplicity,...) run structured debate rounds and a judge decides when convergence is reached.

  • codex-skillscoryparrry

    Agent skills for research, App Store readiness, Codex model routing, repository and Swift review, PR feedback triage, and safe branch cleanup.

  • engineering-foundation-coreEgoistDeveloper

    Task contracts, bounded planning and orchestration, surgical implementation, debugging, research, review, verification, and handoff.

  • bernsteinsipyourdrink-ltd

    The open-source governance layer for AI agents. Spawn parallel agents in per-task git worktrees, verify their work, and merge results; no model in the coordination loop, so replaying a plan reproduces its task graph byte-identically.

Add the verified badge to your README[![Verified by AgentPluginsDirectory.com against Schema 1.0.0](https://agentpluginsdirectory.com/badge.svg)](https://agentpluginsdirectory.com/plugins/axiom)

✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.