appautomaton/automaton

AI coding agent framework — portable, stage-gated harness for Claude Code, Codex, and OpenCode

This repository also configures its own agents. See what automaton tells them →

23Stars on the repository
8Mods indexed here, across every type
1mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

auto-eng-review

01

appautomaton/automaton

Skill Claude CodeCodex

Optional engineering go/no-go on a plan. Use when execution safety needs review before implementation.

not rated 23 1mo ago A 22 tokens original MIT

auto-execute

02

appautomaton/automaton

Skill Claude CodeCodex

Implement approved plan slices. Use as the execute-stage entry point.

not rated 23 1mo ago A SkillSpector: warn 17 tokens original MIT

auto-frame

03

appautomaton/automaton

Skill Claude CodeCodex

Turn a request into a bounded SPEC.md, with as much conversation as it needs. Use to start a change that spans sessions or needs agreed scope.

not rated 23 1mo ago A 33 tokens original MIT

auto-plan

04

appautomaton/automaton

Skill Claude CodeCodex

Turn an approved spec into ordered slices. Use when framing is accepted and planning begins.

not rated 23 1mo ago A SkillSpector: warn 20 tokens original MIT

auto-resume

05

appautomaton/automaton

Skill Claude CodeCodex

Recover active change and next action from artifacts. Use on fresh session with existing work.

not rated 23 1mo ago A SkillSpector: pass 21 tokens original MIT

auto-verify

06

appautomaton/automaton

Skill Claude CodeCodex

Verify completed plan against acceptance criteria. Use after all slices are executed.

not rated 23 1mo ago A 18 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: