wallneradam/claude_autoapprove_mcp
MCP server Claude CodeCodexCursor +2
An MCP server to inject auto-approve MCP functionality into Claude Desktop. Runs locally from the claude-autoapprove-mcp Python package.
Plugin Claude Code
Project memory management with auto-read and dream consolidation.
Instructions file
Claude Code instructions for wallneradam/project-mem-mcp, covering claude.md, project overview, development commands, setup and run the server locally.
Plugin Claude Code
Persistent project memory with automatic consolidation.
Agent
Consolidates a project's MEMORY.md by removing genuinely stale entries, merging near-duplicates, and tightening wording while preserving content. Invoked by the dream skill.
Command
Consolidate and reorganize project memory.
Hook
Runs when a session starts, executing continuous_save_prime.py via uv with --no-project and --quiet. From wallneradam/project-mem-mcp.
Hook
Runs when you submit a prompt, before the agent sees it, executing auto_read.py via uv with --no-project and --quiet. From wallneradam/project-mem-mcp.
Hook
Runs before the agent uses a tool for .*set_project_memory and .*update_project_memory tool calls, executing block_subagent_writes.py via uv with --no-project and --quiet. From wallneradam/project-mem-mcp.
Hook
Runs after a tool call finishes for .*set_project_memory and .*update_project_memory tool calls, executing check_dream.py via uv with --no-project and --quiet. From wallneradam/project-mem-mcp.
Skill Claude CodeCodex
Consolidate and reorganize project memory (MEMORY.md) by invoking the dream-consolidator named subagent (Sonnet, pinned via the agent's model: frontmatter — NEVER pass a model: parameter yourself, it defeats the pin and runs the dream on expensive Opus). The subagent prompt is a CLOSED TEMPLATE: send its fields and…
Skill Claude CodeCodex
Maintain persistent project memory in MEMORY.md via MCP tools. SCOPE: codebase/architecture/conventions/gotchas + Recent Sessions of code work, in /MEMORY.md. DISTINCT from Claude Code's auto memory (/.claude/projects/ /memory/, holds user profile/preferences/feedback). Code-about → here; user-about → auto memory.…
wallneradam/cc-plugin-counterpoint
Plugin Claude Code
Manual collaborative review plugin pairing Claude with Codex CLI — explicit invocation only.
wallneradam/cc-plugin-counterpoint
Plugin Claude Code
Manual collaborative review with Codex — invoked explicitly, multi-round dialogue, chat-visible summaries; stateful code review mode (/review) with autonomous fix loop (/reviewloop); optional user-toggled auto-consult mode (/consulton, /consultoff).
wallneradam/cc-plugin-counterpoint
MCP server Claude CodeCodexCursor
MCP server "counterpoint" as configured in wallneradam/cc-plugin-counterpoint. Runs ${CLAUDE_PLUGIN_ROOT}/server.mjs with node.
wallneradam/cc-plugin-counterpoint
Command
Think through an uncertain problem together with Codex.
wallneradam/cc-plugin-counterpoint
Command
Disable auto-consult mode — stop automatic Codex consultation.
wallneradam/cc-plugin-counterpoint
Command
Enable auto-consult mode — consult Codex on every significant decision.
wallneradam/cc-plugin-counterpoint
Command
Review and stress-test a concrete plan or proposal with Codex (critique mode).
wallneradam/cc-plugin-counterpoint
Command
Reset the counterpoint thread — start a fresh Codex session on the next call.
wallneradam/cc-plugin-counterpoint
Command
Code review of the local git state with Codex (multi-round, stateful findings).
wallneradam/cc-plugin-counterpoint
Command
Autonomous Codex review-and-fix loop on a persistent thread (review, verify, fix, repeat until clean).
wallneradam/cc-plugin-counterpoint
Skill Claude CodeCodex
Collaborative review and problem-solving with Codex CLI via the counterpoint MCP server. Invoke ONLY when the user explicitly asks — through /counterpoint, /consult, or a direct request for a second opinion. Do NOT invoke proactively, do NOT invoke "before finalizing", do NOT treat any other situation as a trigger.…