Ecosystem Update - 2026-05-08

TL;DR

• OpenAI Codex 0.129.0 shipped on 2026-05-07; the useful deltas for this setup are /hooks, broader hook lifecycle support, workspace-aware /diff, stronger plugin sharing controls, and TUI ergonomics.
• The current harness already has the main high-leverage primitives: gpt-5.5, danger-full-access with approval never, omni-mem hooks, OpenAI docs MCP, custom read-only reviewers, planning-gate, auto/govern wrappers, and browser/plugin support.
• Safe Quick Wins were limited to config/agent metadata: a config schema hint plus display nicknames for the highest-use custom agents. Riskier items stay in Build Queue.

Quick Wins

Auto-Implemented

• Added #:schema https://developers.openai.com/codex/config-schema.json to ~/.codex/config.toml.
• Added display-only nickname_candidates to ~/.codex/agents/worker.toml, ~/.codex/agents/explorer.toml, and ~/.codex/agents/reviewer.toml.
• Backup created first under ~/.codex/backups/2026-05-08/.
• Verified with python3/tomllib for ~/.codex/config.toml plus all ~/.codex/agents/*.toml, and python3 -m json.tool ~/.codex/hooks.json.
• Saved durable omni-mem summary: Ecosystem update 2026-05-08 quick wins.

Build Queue

• Codex 0.129.0 upgrade check (Codex-md) - https://github.com/openai/codex/releases/tag/rust-v0.129.0 - Current local CLI is codex-cli 0.128.0; 0.129.0 includes /hooks, hooks before/after compaction, plugin sharing/source filtering, workspace-aware /diff, and TUI improvements. Worth a deliberate upgrade plus smoke test, not an automatic ecosystem edit.
• Hook lifecycle review for 0.129.0 (hook) - https://developers.openai.com/codex/hooks - Current hooks.json uses SessionStart, Stop, and PreCompact. After upgrading, review whether existing scripts should be wired into supported PreToolUse, PostToolUse, PermissionRequest, or post-compaction events. Do not wire anything until the target event and existing script contract are confirmed.
• Permission profile audit (Codex-md) - https://developers.openai.com/codex/config-reference#configtoml - Official config now exposes named default_permissions and [permissions.<name>]. The current power-user posture is intentionally danger-full-access; a useful next step is a non-default review/ci profile, not replacing the default.
• Plugin sharing and marketplace hygiene pass (mcp) - https://github.com/openai/codex/releases/tag/rust-v0.129.0 - 0.129.0 improves workspace sharing, source filtering, marketplace removal/upgrades, and admin-disabled handling. Check installed marketplaces after the CLI upgrade.
• Codex native memories pilot (skill) - https://github.com/shanraisshan/codex-cli-best-practice - Native [features].memories is now documented, but this setup already uses omni-mem as the source of truth. Pilot only if it can run with no_memories_if_mcp_or_web_search = true and without duplicating durable memory paths.
• AgentLint-style compatibility audit (skill) - https://github.com/rohitg00/awesome-claude-code-toolkit - The toolkit highlights AI-agent compatibility linting. This should become a small Codex-owned audit skill only if current codex-runtime-doctor cannot cover the same checks.

Research

• A Self-Improving Coding Agent - Directly relevant to the evolve/autoconfig loop: use benchmark-scored, reversible self-edits rather than broad runtime rewrites.
• Memory for Autonomous LLM Agents: Mechanisms, Evaluation, and Emerging Frontiers - Useful for omni-mem: reinforces write filtering, contradiction handling, latency budgets, privacy governance, and explicit write-manage-read loops.

Already Have

AGENTS.md runtime contract, byte-identical ~/.codex/AGENTS.md and ~/AGENTS.md, gpt-5.5 default model, approval never, danger-full-access, prompt telemetry off, OpenAI developer docs MCP, omni-mem MCP plus Stop/PreCompact hooks, startup repo-context hook, custom read-only reviewer/explorer/planner/validator agents, worker agent, [agents] thread caps, planning-gate, auto/govern/drive/build wrappers, session recall, skill audit, browser-use, playwright, documents, spreadsheets, presentations, Gmail, security-audit, codex-security, skills-janitor, autoconfig, evolve, build-backlog, ecosystem-update state tracking, official plugin marketplaces, and active Codex hooks feature flag.

Rejected

• Install Claude toolkit wholesale - Overengineered and Claude-owned; adapt discrete ideas into Codex-owned surfaces instead.
• Enable native Codex memories immediately - Already covered by omni-mem; enabling a second memory system without a pilot risks duplicate recall and privacy confusion.
• Add new hook wiring that needs new scripts - The skill explicitly forbids new-script hook Quick Wins. Existing scripts must be reviewed against current hook input/output contracts first.
• Upgrade to 0.130.0 alpha releases - Current 0.130.0 artifacts are prerelease alphas from 2026-05-08. Use stable 0.129.0 for the next upgrade check.
• Change constitutional policy docs - ~/.codex/AGENTS.md and ~/AGENTS.md are hard-limited out of Quick Wins.
• Deploy website or wrapper output - Out of scope per user instruction; wrapper owns render/deploy after completion.

Sources checked: https://github.com/hesreallyhim/awesome-claude-code, https://howborisusesclaudecode.com/, https://github.com/shanraisshan/codex-cli-best-practice, https://arxiv.org/search/?searchtype=all&query=LLM+agent+coding&order=-announced_date_first, https://github.com/rohitg00/awesome-claude-code-toolkit, https://developers.openai.com/codex/, https://developers.openai.com/codex/config-reference, https://developers.openai.com/codex/hooks, https://github.com/openai/codex/releases, https://github.com/openai/codex/releases/tag/rust-v0.129.0, https://arxiv.org/abs/2504.15228, https://arxiv.org/abs/2603.07670 Tier 2 fetched: yes Tier 3 fetched: yes Run at: 2026-05-08T15:37:21Z