Ecosystem Update — 2026-05-04
Highlights
- Anthropic's hook spec has crept further than last cycle suggested:
PostToolBatch,UserPromptExpansion,PermissionDenied,Setup,TeammateIdle, and the MCPElicitation/ElicitationResultpair are all confirmed in the official docs.PostToolBatchis the highest-leverage of the new events because it gives a single deterministic hook point after parallel tool-batches resolve — currently nothing observes that boundary - The two events flagged as Build Queue on 2026-05-01 (
ConfigChange,InstructionsLoaded) are confirmed in the official spec. They're still missing from the wired set - Tier 1 sources (awesome-claude-code, Boris) are stale this cycle — awesome-claude-code is in catalog-rewrite, Boris hasn't posted since 2026-04-16. Real signal this cycle came from the official hooks doc and the 2604/2605 arxiv batch
Quick Wins (implemented today)
-
PermissionDeniedhook withretry: truehook
New Tools, Skills & Patterns
-
PostToolBatchhook hookFires after a full batch of parallel tool calls resolves, before the next model call. Genuine gap: parallel tool-batches (multiple WebFetch/Read/Grep in a single response) are now the dominant pattern, but no current hook observes the *batch boundary* -
UserPromptExpansionhook hookthe route classifier inUserPromptSubmitonly sees the bare slash command, not the expanded prompt -
Setuphook hookFires only on--init/--maintenance. Useful for one-time dependency installation that shouldn't run on every SessionStart (currentSessionStarthooks do too much work because there's no init/maintenance split) -
TeammateIdlehook hookFires when an agent-team teammate is about to go idle; exit 2 keeps it working. Direct application: prevent the worker subagent from going idle mid-slice when the reviewer is still validating -
Elicitation/ElicitationResulthooks hookFires when an MCP server requests user input mid-tool-call. Currently any MCP-side elicitation blocks autonomous runs because there's no programmatic responder -
ConfigChangehook hookNow confirmed in official docs with matchersuser_settings,project_settings,local_settings,policy_settings,skills. Exit 2 to block changes during critical execution windows -
InstructionsLoadedhook hookConfirmed; matcherssession_start,nested_traversal,path_glob_match,include,compact -
agent-type hook hook-typeReplaces shell-script greps in PreToolUse with a real LLM-verifier subagent. Highest-leverage primitive when added; still requires a verifier-prompt design pass before flipping it on -
http-type hook hook-typeLower priority thanagent-type -
Anthropic-managed Routines featurepushing this up the queue
-
claude-code-showcase referenceNew this cycle. Reference repo for hooks + skills + agents + GitHub Actions wiring. Possibly useful as a structural reference; not as a runtime install
-
hook-development skill skillNew this cycle. Scaffolds a hook with the right JSON-output shape. Worth installing if hook authoring becomes recurring; small enough that copying the patterns is also fine
Research Worth Reading
-
arXiv:2605.00798 — RunAgent: Constraint-Guided Plan ExecutionMulti-agent execution with explicit control constructs (IF, GOTO, FORALL) and autonomous constraint derivation
-
arXiv:2605.00803 — AutoMat: Coding-Agent Reproduction BenchmarkOnly 54.1% success reproducing computational-materials-science claims due to incomplete procedures and execution fragility. Useful as a failure-mode taxonomy when designing task decomposition and recovery in autonomous harnesses
-
arXiv:2605.00557 — SCISENSE: Structured Sensemaking for Coding AgentsTargeted ideation trajectories improve artifact quality and executability vs. unconstrained exploration. Evidence for pre-execution planning gates as a quality lever, not just a process formality
-
arXiv:2605.00505 — LLM-Oriented IR: Denoising-First RetrievalReframes retrieval around signal-to-noise optimization for agentic search
Considered, Not Adopting
Items reviewed and explicitly declined this cycle, with the reason. Curation discipline matters more than coverage.
- Claude Forge wholesale install — same rejection as 2026-05-01; the 11 agents / 36 commands / 15 skills bundle would duplicate existing primitives and violates the simplicity budget
- VoltAgent awesome-agent-skills (1000+ skills) — bulk import is an anti-pattern; cherry-pick if a specific skill matches a recurring need (none identified today)
- flonat/claude-research — academic-workflow specific, wrong domain
- Jeffallan/claude-skills (broad catalog) — same simplicity-budget rejection as alirezarezvani last cycle
- arXiv:2605.00505 LLM-Oriented IR — as Quick Win — interesting but research, not a config change
- arXiv:2604.26235 LATTICE crypto-agent benchmark — wrong domain (crypto copilots)