Astra Flash Orchestrator

Astra Advisor is a Codex plugin for capability-routed software delivery from DannyMac180. GPT-6 Astra acts as the primary architect and acceptance owner: it plans work, decides whether bounded independent tasks should be delegated, selects supported native subagent models and reasoning effort, and continues parent-session work while delegations run. It uses the exposed collaboration tool to route tasks among Sol, Terra, and Luna subagents, then inspects the complete diff, reruns requested checks, and sends substantial changes to a fresh read-only reviewer; work is accepted only after the reviewer returns "ship". Each delegation reports its selected and runtime-observed settings, and tasks can end with an API-equivalent cost receipt that compares observed token usage with a versioned Astra pricing snapshot. It can be installed as a plugin in a current Codex CLI or ChatGPT desktop app with plugins enabled. The README notes that ChatGPT Work cloud tasks currently cannot provide arbitrary model or effort controls, so Astra does not dispatch model-pinned requests there by default.

An open-source Codex configuration that uses Astra as the root orchestrator and independent reviewer, with Luna-based subagents for exploration, implementation, testing, and research. It provides separate Pro and Plus profiles, TOML role configurations, an Astra orchestrator skill, project-level AGENTS.md instructions, and shell and PowerShell installers that copy the selected configuration into a target repository. The profiles set model, reasoning-effort, approval, sandbox, and concurrent-thread settings, while named role files can override the defaults. The repository also includes guides for orchestration patterns, plan-specific setup, iteration, and token-usage reporting from Codex session logs. It is licensed under Apache License 2.0.

DeepSeek and Destroy (DSD) is a long-horizon coding-agent skill for executing large implementation plans through persistent worker loops. A premium parent agent handles architecture, decomposition, decisions, and phase gates, while fresh lower-cost specialist workers implement, review, repair, and recheck repository-scale changes. The default worker backend is external OpenCode using opencode-go/deepseek-v4-flash, and the skill is designed for Codex, Claude Code, OpenCode, Kilo Code, and comparable coding harnesses. Each task is rendered into an immutable JSON contract and managed through attempt directories containing prompts, reports, logs, state, and scope baselines. Its normal loop uses an Implementer, a fresh independent Reviewer, and—when needed—a fresh Fixer followed by another Reviewer. Python-based gates check objective integrity such as hashes, lifecycle, and exact source movement; an optional read-only Evidence Clerk interprets already-produced evidence for the parent but cannot invent proof, rerun verification, repair code, waive integrity failures, approve work, or recurse into another Clerk. Documentation is split between always-relevant parent rules and cold-loaded workspace, harness, transport, compaction, prompt, and specialist-role materials.

Fable orchestrator is a small, local-first routing skill for Codex that separates planning and adjudication from code implementation. Fable 5.1 plans tasks and makes final decisions without writing code or owning the workspace; Codex validates the bounded graph it returns, runs ready implementation nodes in parallel when useful, collects evidence, verifies the result, and requests further adjudication when needed. Implementation work is delegated through callable OpenCode Go agents, with GPT-5.6 Luna assigned to normal implementation and DeepSeek V4 Flash to loops and repeated high-throughput execution. The repository contains an installable skill, agent configuration, an invocation script, an installer, and shell-based tests. It does not provide a proxy, dashboard, model catalog, credential store, or API-key management. The installer supports dry runs, copying into a Codex skills direct

Codex Orchestration is a Codex plugin that coordinates multiple models and role-based stages within a single task. It can assign optional Planner, Advisor, and Designer roles, plus a required Executor; the selected Codex model passes work between them, checks each result, and returns the final answer. The Planner creates and revises a plan, the Advisor reviews it and can return PLAN_APPROVED, the Designer produces an optional visual or UX handoff, and Executors implement the approved plan, potentially in parallel. The workflow stops after approval or after a safety limit of eight reviews, showing unresolved issues if approval is not reached. It is installed through the Codex plugin marketplace and requires Python 3.11 or newer.