Ecosystem Update — 2026-04-05
Highlights
- Auto-mode (background safety classifier) eliminates permission prompts — platform feature, just enable
- Preflight MCP catches vague/underspecified prompts before they waste cycles — 24-tool server, one install
- SkillDeck gives a local dashboard to manage all Claude Code config in one place — visual skills/hooks/agents/settings management
Quick Wins (implemented today)
-
auto-mode hookEnable background safety classifier in settings — replaces manual permission prompts with auto-classification
-
preflight mcpInstall 24-tool MCP server that scores prompt clarity, estimates cost, catches vague requests before execution
-
skilldeck mcpInstall local dashboard to manage skills, agents, teams, commands, hooks, settings, and CLAUDE.md visually
-
once-true-hooks hookAdd
once: trueto one-shot hooks (session-start, preflight) to prevent duplicate execution
New Tools, Skills & Patterns
-
harness skillMeta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use. Could auto-scaffold new project agent configurations
-
codetape hookFlight recorder for AI coding sessions — auto-records semantic traces, syncs README/CHANGELOG. Useful for audit trail
-
bouncer hookIndependent quality gate using Gemini to audit Claude Code output. Cross-model verification adds a second opinion
-
channels hookPush events from Telegram, Discord, or webhooks into running sessions. Enables async notification beyond desktop
-
ccmanager mcpMulti-agent session manager supporting Claude Code, Gemini, Codex, Cursor, Copilot. Unified orchestration across models
-
claude-devtools mcpDesktop observability app: turn-based context data, compaction visualization, subagent execution trees. Good for debugging complex agent runs
-
ultraplan agent-patternDraft plans in cloud with browser review, inline comments, flexible execution. Planning-gate alternative with visual review
Research Worth Reading
-
Agentic Verification of Software SystemsAutoRocq: first LLM agent for program verification via iterative refinement with theorem prover. Applicable to generate-and-validate loops in multi-agent coding
-
AgentSpec: Customizable Runtime EnforcementFramework for safe LLM agent operation through customizable runtime enforcement policies. Directly relevant to governance/routing
-
DeepCode: Open Agentic CodingAutonomous document-to-codebase synthesis with structured indexing and closed-loop error correction. Parallels to 's spec→code pipeline
-
PRDJudge: Automated Code ValidationLightweight evaluation agent that auto-validates code agent output using executable tests. Could enhance
-
From LLM Reasoning to Autonomous AI AgentsComprehensive review of autonomous agent architectures — planning, tool use, memory, multi-agent collaboration. Good survey of the landscape
Considered, Not Adopting
Items reviewed and explicitly declined this cycle, with the reason. Curation discipline matters more than coverage.
- claude-recap — claude-mem with semantic search + type tagging; claude-recap is shell-hook markdown only. Covered by existing primitive
- fractal — (recursive project management) — Predicate decomposition is interesting but planning-gate + build skill already handle task breakdown. Adding a new decomposition engine = overengineering
- vibe-kanban — Kanban board + worktree orchestration. Our govern skill already routes and tracks work packets. Redundant orchestration layer
- oh-my-claudecode — Teams orchestration with 19 agents. Adding another 19-agent framework = complexity without proof of gap
- agent-teams-exercises — Educational repo, not a tool. No action needed
- reporecall — AST-indexed codebase memory. We have Grep/Glob + claude-mem. No proof existing primitives can't cover this