Ecosystem Update - 2026-05-17

TL;DR

• One safe harness Quick Win was implemented: added a non-default conservative profile to ~/.codex/config.toml for on-request approvals, workspace-write sandboxing, and cached web search.
• Today's Tier 1 sources mostly reinforced patterns this setup already has: subagents, hooks, side conversations, profiles, skill progressive disclosure, worktrees, session recall, and explicit verification.
• The strongest new watch item is first-class skill lifecycle hooks (PreSkillUse/PostSkillUse), but it is an upstream Codex feature request and not safe to wire locally until the runtime supports those events.

Quick Wins

Auto-Implemented

• Backed up config.toml, hooks.json, and all current agent TOMLs under /Users/chadsimon/.codex/backups/2026-05-17/.
• Added [profiles.conservative] to /Users/chadsimon/.codex/config.toml.
• Verified hooks.json parses with python3 -m json.tool, config.toml parses with tomllib, codex --profile conservative --version exits cleanly, and codex --profile conservative features list still shows hooks, plugins, multi_agent, tool_search, and unified_exec available.
• Ran python3 ~/.codex/bin/codex-runtime-doctor; the new config passed, but the doctor exited with the pre-existing local Docker/omni-mem availability error and one LaunchAgent warning.

Build Queue

• PreSkillUse/PostSkillUse hook watch (hook) - openai/codex#17132 - Once Codex supports first-class skill lifecycle events, add a no-prompt-logging adapter for local skill audit telemetry and skill invocation summaries. Current hooks.json cannot safely implement unsupported events.
• Conservative profile hardening pass (Codex-md) - OpenAI config reference - Profile-scoped sandbox_workspace_write.network_access is not present in the current schema; evaluate a custom permissions profile or future schema support before making the conservative profile network-restricted.
• External Codex skill catalog intake (skill) - ComposioHQ/awesome-codex-skills, Gitmaxd/deepagents-cli-codex-skill - Audit specific skills such as migration-auditor or unslop through codex-skill-audit --strict; do not import catalogs wholesale.
• Self-evolving runtime stability eval (research) - Self-Evolving Software Agents - Add an evolve/autoconfig evaluation that checks behavioral inheritance and stability before any autonomous runtime self-modification is promoted.

Research

• Self-Evolving Software Agents - Relevant to evolve and autoconfig; useful as a cautionary frame for verifying stability before runtime self-modification.
• Autonomous LLM Agent Worms - Already tracked, but still reinforces the current no-wholesale-import posture for skills/plugins and the need for trusted memory promotion.
• No new last-24-hour arXiv coding-agent paper surfaced from the web crawl. The direct arXiv export API returned HTTP 429, so this run used web-search results for the research pass.

Already Have

gpt-5.5 power-user default, approval_policy = "never", sandbox_mode = "danger-full-access", prompt telemetry off, live web search, schema-linked config.toml, features.hooks = true, plugin support, goals support, OpenAI developer docs MCP with parallel calls, omni-mem MCP configured, Stitch MCP, Numerai MCP, Browser/Computer Use/Documents/Spreadsheets/Presentations/Gmail plugins, Bash PreToolUse safety guard, Bash PostToolUse verification ledger, Bash failure-context hook, SessionStart startup/resume repo-context preflight, Stop omni-mem save hook, PreCompact omni-mem hook, read-only explorer/planner/reviewer/python-reviewer/typescript-reviewer/validator agents, scoped worker and chad-twin agents, bounded agent depth/thread/runtime caps, profiles.review, profiles.conservative, tools.view_image, /side, /statusline, /title, /fork, /resume, codex-skill-audit --strict, session-recall, rlm-scan, planning-gate, auto, drive, go, codex-security, security-audit, codex-runtime-doctor, what-would-chad-do, and current stable codex-cli 0.130.0.

Rejected

• Enable native Codex memories as a Quick Win - rejected because omni-mem is the canonical memory system on this machine and native memories remain experimental/off by default.
• Enable plugin hooks automatically - rejected because plugin-bundled hooks require trust review before execution.
• Wholesale import Deep Agents CLI or awesome-codex-skills - rejected because outside skills must pass codex-skill-audit --strict and should be imported only for a concrete recurring workflow.
• Prompt telemetry through UserPromptSubmit - rejected because global prompt telemetry is opt-in and this runtime explicitly keeps user prompt logging disabled by default.
• Add PreSkillUse/PostSkillUse to hooks.json now - rejected because those events are an upstream feature request, not a supported local hook surface.
• Edit AGENTS.md as a Quick Win - rejected by the ecosystem-update hard limit; constitutional policy docs require explicit direction.

Sources checked: https://github.com/hesreallyhim/awesome-claude-code, https://howborisusesclaudecode.com/, https://github.com/shanraisshan/codex-cli-best-practice, https://github.com/openai/codex/issues/17132, https://github.com/openai/codex/issues/21639, https://github.com/openai/codex/issues/21753, https://github.com/openai/codex/issues/17331, https://github.com/ComposioHQ/awesome-codex-skills, https://github.com/Gitmaxd/deepagents-cli-codex-skill, https://developers.openai.com/codex/config-reference, https://developers.openai.com/codex/config-schema.json, https://arxiv.org/search/?searchtype=all&query=LLM+agent+coding&order=-announced_date_first Tier 2 fetched: yes via web search; direct arXiv export API returned HTTP 429 Tier 3 fetched: no; weekly sources were fetched on 2026-05-16T10:36:23Z omni-mem write: skipped; local Docker/localhost omni-mem service was unavailable Run at: 2026-05-17T10:35:08Z