Ecosystem Update - 2026-05-18

May 18, 2026 · curated by Chad Simon · 20 items reviewed

Highlights

Two safe config-only Quick Wins were implemented: disabled the placeholder pokegen skill globally and added an optional conservative-auto-review profile
Today's community sources mostly reinforce what this setup already has: compact AGENTS policy, hooks, role-specific subagents, skill progressive disclosure, live web search, and verification-first closure
The strongest new research signal is cost-aware agent design: programmatic state/context beats deeper deliberation, and coding-agent context pruning deserves a local eval before implementation

Placeholder pokegen skill disable skill

developers.openai.com

Add global [[skills.config]] with enabled = false for /Users/chadsimon/.agents/skills/pokegen
Conservative auto-review profile Codex-md

developers.openai.com

Add non-default [profiles.conservative-auto-review] using workspace-write, on-request, cached web, and approvals_reviewer = "auto_review"

Granular approval policy profile Codex-md

developers.openai.com

OpenAI config reference - Design a named profile that uses approval_policy.granular for rule, MCP elicitation, request-permission, and skill-approval prompts; do not make it default until prompt categories are tested locally
cc-discipline-style edit-loop guard hook

github.com/rohitg00/awesome-claude-code-toolkit

awesome-claude-code-toolkit - Current hooks record verification and block catastrophic shell commands, but do not hard-stop repeated edit loops or skipped verification streaks; this needs a new local script, so it is not a Quick Win
llm-prices MCP cost intake mcp

github.com/rohitg00/awesome-claude-code-toolkit

awesome-claude-code-toolkit commit stream - Audit whether a model-pricing MCP can inform autoconfig or route selection without adding a new dependency to normal turns
Property-guided closure checks

arXiv

Property-Guided LLM Program Synthesis for Planning - Convert closure criteria into counterexample-producing predicates for task evals where concrete properties exist
Agent skill scoping smoke skill

github.com/openai/codex

openai/codex#14161 - Verify current CLI behavior for agent-local [[skills.config]] before relying on per-agent skill allow/deny rules

Context Pruning for Coding Agents via Multi-Rubric Latent Reasoning

arXiv

- Strong fit for rlm-scan and retrieval hygiene: separates semantic evidence from dependency support and reports token savings on multi-turn coding tasks
Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDP

arXiv

- Directly relevant to current subagent discipline: clean decomposition and programmatic state beat stacked deliberation in their setting
Look Before You Leap: Autonomous Exploration for LLM Agents

arXiv

- Supports the existing discover-before-edit posture and suggests a measurable exploration coverage metric
FORGE: Self-Evolving Agent Memory With No Weight Updates via Population Broadcast

arXiv
TopoEvo: A Topology-Aware Self-Evolving Multi-Agent Framework for Root Cause Analysis in Microservices

arXiv

- Useful pattern for incident skills: Hypothesis-Evidence-Test workflows and topology-grounded evidence
CAPS: Cascaded Adaptive Pairwise Selection for Efficient Parallel Reasoning

arXiv

- Candidate-selection idea for parallel agents: spend verifier tokens adaptively instead of pairwise-reviewing everything at full context
CAX-Agent: A Lightweight Agent Harness for Reliable APDL Automation

arXiv

- Reinforces deterministic recovery ladders: rule patching, model regeneration, context enrichment, then human intervention

Items reviewed and explicitly declined this cycle, with the reason. Curation discipline matters more than coverage.

Upgrade to 0.131.0-alpha.22 — - rejected as a Quick Win because it is still a pre-release and the current global posture forbids enabling under-development runtime features globally without rollback notes and validation
Wholesale install cc-discipline or Claude toolkit hooks — - rejected because outside hooks/scripts must be audited and adapted to Codex-owned surfaces before execution
Set allow_login_shell = false globally — - rejected because this machine relies on zsh/login-shell behavior in normal command execution; evaluate only as a profile-specific hardening pass
Enable plugin_hooks automatically — - rejected because plugin-bundled hooks are still under-development and require trust review
Enable native Codex memories
Edit AGENTS.md as a Quick Win — - rejected by the ecosystem-update hard limit; constitutional policy changes require explicit direction