Ecosystem Update - 2026-06-17
TL;DR
- Implemented one safe harness Quick Win:
CODEX_DISABLED_HOOKSnow lets hook profiles suppress named hooks at runtime without editinghooks.json. - Today's Tier 1 signal reinforces context isolation, workflow triggers, and hook runtime controls; this setup already has most of the useful primitives.
- No new hook wiring, policy-doc edits, plugin-hook enablement, native memories, or deeper nested agents were applied because they either require trust review, violate current posture, or exceed Quick Win scope.
Quick Wins
| Item | Source | Type | Impact | Effort | Action |
|---|---|---|---|---|---|
| Runtime disabled-hook list | https://github.com/mturac/everything-openai-codex | hook | 2 | 1 | Add CODEX_DISABLED_HOOKS handling to existing hook_profile.py profile gate |
Auto-Implemented
- Runtime disabled-hook list - Updated
/Users/chadsimon/.codex/bin/hook_profile.pysoCODEX_DISABLED_HOOKS=hook_a,hook_bdisables specific hook ids before profile checks. Verified withpython3 -m py_compile /Users/chadsimon/.codex/bin/hook_profile.py, a normal minimal-profile check, and a disable-list behavior check.
Build Queue
- Nested subagent depth eval (agent-pattern) - https://howborisusesclaudecode.com/ - Boris's latest nested-agent guidance argues for deeper delegated context isolation. Current Codex config pins
agents.max_depth = 1; evaluate a temporarymax_depth = 2profile only under explicit autonomous-lab rollback notes before considering any default change. - Forked skill context compatibility audit (skill) - https://howborisusesclaudecode.com/ - Claude's
fork: trueskill isolation maps partly to Codex/forkand side-thread primitives, but Codex skills do not expose that frontmatter. Build a compatibility note or eval instead of adding unsupported metadata. - Portable skill sanity-test harness (skill) - https://github.com/grahama1970/agent-skills - The shared skill catalog includes
skills/run-all-sanity.shas a pattern. This setup hasskill-auditand many skills, but no single local sanity pass that verifies installed skill metadata plus referenced files and scripts across all roots. - Portability fidelity rubric (skill) - https://github.com/camoa/claude-skills/blob/main/PORTABILITY.md - The portability guide separates portable
SKILL.mdknowledge from non-portable commands/agents/hooks. Turn that into a local audit mode for outside skill intake so Codex can classify "knowledge only" vs. "workflow fidelity lost" before installing. - Adaptive reasoning-effort watch item (agent-pattern) - https://github.com/openai/codex/issues/26961 - Community request asks for hooks/profile managers to adjust reasoning effort dynamically. Current setup has a prompt route classifier, but Codex does not expose a stable hook output to mutate effort mid-session, so this remains a watch item.
Research
- No arXiv Tier 2 papers fetched. The prior Tier 2 run was
2026-06-16T06:32:36-04:00, and today's crawl began at2026-06-17T06:30:59-04:00, still inside the 24-hour gate.
Already Have
Hooks enabled with canonical features.hooks, Bash pre-tool guard, PostToolUse verification ledger, tool-failure context, UserPromptSubmit route classifier, SessionStart startup/resume/clear/compact coverage, omni-mem Stop and PreCompact hooks, hook profile gating, command execpolicy rules for destructive git/rm variants, read-only reviewer/explorer/planner/validator agents, conservative and review profiles, OpenAI developer docs MCP with parallel calls, plugins enabled with plugin hooks disabled, prompt telemetry disabled, Codex-owned AGENTS.md fallback only, check_for_update_on_startup, desktop notifications, /fork and /resume support from current Codex, session search via codex-session-search, skill audit tooling.
Rejected
- Raise
agents.max_depthfor nested subagents - Rejected as a Quick Win because it increases autonomous fan-out and cost. Evaluate under a temporary profile first. - Add
fork: trueto local skills - Rejected because Codex does not document that skill frontmatter; unsupported metadata would be noise. - Enable plugin hooks globally - Rejected because current posture keeps
plugin_hooks = false, and official docs require hook trust review for plugin-bundled hooks. - Wire new Stop validation hooks immediately - Rejected because prior state already tracked stop-gate wiring, existing hooks require trust hashes, and new/changed non-managed hooks are skipped until trusted.
- Bootstrap AGENTS.md from an external repo each session - Rejected because this machine owns
~/.codex/AGENTS.mdand~/AGENTS.mdbyte identity; self-updating policy docs conflict with runtime ownership. - Wholesale install shared skill/hook catalogs - Rejected because outside skills require strict audit first and many catalog hooks target Claude paths or unknown trust semantics.
- Switch to Claude/Fable model guidance - Rejected because it is not a Codex runtime target and does not map to the configured OpenAI model posture.
Sources checked: https://github.com/hesreallyhim/awesome-claude-code, https://howborisusesclaudecode.com/, https://github.com/shanraisshan/codex-cli-best-practice, https://github.com/grahama1970/agent-skills, https://github.com/composiohq/awesome-codex-skills, https://github.com/camoa/claude-skills/blob/main/PORTABILITY.md, https://github.com/openai/codex/issues/26961, https://github.com/yzhao062/anywhere-agents/blob/main/AGENTS.md, https://github.com/mturac/everything-openai-codex, https://developers.openai.com/codex/hooks Tier 2 fetched: no Tier 3 fetched: no Run at: 2026-06-17T06:30:59-04:00