MCP server Claude CodeCodexCursor +2
MCP server "cochlea-mcp" as configured in richer-richard/cochlea. Launched with https://github.com/richer-richard/cochlea/releases/download/cochlea-mcp-v0.7.0/c.
Instructions file CodexOpenCode
Instructions for richer-richard/fenestra, covering building fenestra uis as an agent, the loop, driving a real app: the harness, json scenarios (no recompile) and asserting structure (accessibility tree).
Instructions file
Instructions for richer-richard/fenestra, covering claude.md, project and working rules.
MCP server Claude CodeCodexCursor +2
MCP server "fenestra-mcp" as configured in richer-richard/fenestra. Launched with https://github.com/richer-richard/fenestra/releases/download/fenestra-mcp-v0.40..
Plugin Claude Code
Self-hosted single-plugin marketplace for cc-research — multi-agent deep research on Claude models.
Instructions file CodexOpenCode
AGENTS.md instructions for richer-richard/cc-research, covering agents.md — codex guide for the cc-research monorepo, codex plugin layout (plugin-codex/), conventions (match these when editing the codex plugin), build / test the codex plugin and don't.
Hook
Runs when the agent finishes a response, executing audit.py via python3. From richer-richard/cc-research.
Skill Claude CodeCodex
Multi-agent deep research on Codex. Use for questions that need many sources and a written, fully-cited report — "research X", "deep dive on X", "compare X vs Y", "should I adopt / build on X". Breaks the question into independent strands, spawns researcher subagents in parallel, triangulates the evidence, synthesizes…
Plugin Claude Code
Multi-agent deep research on Claude models: orchestrator -> parallel researcher subagents -> triangulate -> synthesize -> cite -> report. Built-in tools only (WebSearch, WebFetch, Read, Grep, Glob, Write, Task); no external research APIs or MCP servers.
Agent
Local-file research subagent that executes ONE strand against files on disk (the repo / working directory) instead of the web. Uses Read, Grep, Glob to gather evidence and returns it in the per-strand shard format for the orchestrator to persist. The orchestrator dispatches up to 3 of these when local sources are…
Agent
Web research subagent that executes exactly ONE research strand. Searches and fetches web sources, extracts atomic claims, scores each source's quality, and writes its OWN two evidence files in the run directory. The orchestrator dispatches one per independent strand, many in parallel.
Agent
Report-writer subagent (final stage). Reads ALL per-strand evidence files in a run directory and writes a well-structured, fully-cited report.md. It reads everything from disk so it is robust to context compaction. The orchestrator invokes it once, after retrieval is complete.
Command
Deep research on Claude models — full multi-agent loop, plan-only, or resume a run. Persists cited evidence to runs/ /.
Skill Claude CodeCodex
The cc-research deep-research loop. Use when running the /research command or the cc-research SDK to plan independent research strands, dispatch many researcher subagents in parallel via Task, triangulate evidence, synthesize a fully-cited report, and persist everything to a resumable run directory. Defines the three…