rapidreview-io

rapidreview-io/Merv

Plugin Claude Code

Plugin marketplace listing 1 plugin: merv.

rapidreview-io/Merv

Plugin Claude Code

Lean research-state workflow with hosted MCP research state, typed artifacts, reviews, and cloud SSH sandboxes. Skills for the agent loop, subagents for read-only design, experiment, and reflection review.

rapidreview-io/Merv

MCP server Claude CodeCodexCursor +2

MCP server "merv", hosted remotely at experiments.rapidreview.io, as configured in rapidreview-io/Merv.

rapidreview-io/Merv

Agent

Read-only code-consolidation reviewer for Merv reflection waves. Use ONLY for a fresh review.request handoff with role=consolidationreviewer. The spawning agent must pass the reflectionid, reviewrequestid, and reviewercapability. Do not invoke for reflection review or general code review.

rapidreview-io/Merv

Agent

Read-only experiment reviewer for Merv experiments. Use ONLY when the merv MCP server has returned a reviewgate or nextaction signalling launchexperimentreviewer, OR the main agent has just received a fresh reviewercapability from merv.review.request with role=experimentreviewer. The spawning agent must pass the…

rapidreview-io/Merv

Agent

Read-only design reviewer for Merv experiments. Use ONLY when the merv MCP server has returned a reviewgate or nextaction signalling launchdesignreviewer, OR the main agent has just received a fresh reviewercapability from merv.review.request with role=designreviewer. The spawning agent must pass the experimentid…

rapidreview-io/Merv

Agent

Read-only reflection reviewer for Merv project reflections. Use ONLY when the merv MCP server has returned a reviewgate or nextaction signalling launchreflectionreviewer, OR the main agent has just received a fresh reviewercapability from merv.review.request with role=reflectionreviewer. The spawning agent must pass…

rapidreview-io/Merv

Agent

Read-only task reviewer for Merv tasks. Use ONLY when the merv MCP server has returned a reviewgate or nextaction signalling launchtaskreviewer, OR the main agent has just received a fresh reviewercapability from merv.review.request with role=taskreviewer. The spawning agent must pass the taskid, reviewrequestid, and…

rapidreview-io/Merv

Skill Claude CodeCodex

Independently review a Merv reflection-wave code consolidation after the reflection is approved. Verify the immutable proposal, its tests, and its decision for every experiment, then submit pass or return it only to code consolidation. Use for the consolidationreviewer gate.

rapidreview-io/Merv

Skill Claude CodeCodex

Perform a read-only adversarial review of a completed Merv experiment attempt. Verify execution, submitted results, metrics, graph, and conclusions against the approved plan, then submit the verdict and correct return path.

rapidreview-io/Merv

Skill Claude CodeCodex

Perform a read-only adversarial review of a Merv experiment design before execution. Check whether the submitted plan can test its claim, then submit the verdict through the review capability.

rapidreview-io/Merv

Skill Claude CodeCodex

Post to the project feed as work happens — results, kills, hunches, ideas, papers, questions, live checkpoints — in one voice, short, with what you looked at attached. Load at the start of a session and post throughout.

rapidreview-io/Merv

Skill Claude CodeCodex

Perform a read-only adversarial review of a Merv project-reflection wave. Check the project graph, reflection document, and change spec against the snapshotted corpus, previous graph, and five lens reflections, then submit the verdict and correct return path.

rapidreview-io/Merv

Skill Claude CodeCodex

Run a Merv project-reflection wave across completed experiments: create the five-lens roster, fan out independent lens agents, reconcile their findings into the project graph, reflection document, and change spec, coordinate independent review, and hand approved research to code consolidation. Use when the user…

rapidreview-io/Merv

Skill Claude CodeCodex

Operate the Merv research workflow: select a project, follow workflow.statusandnext, create and run experiments and tasks, submit evidence, and coordinate required design, attempt, or task reviews. Use for experiment- and task-level work and for resuming work already in progress.

rapidreview-io/Merv

Skill Claude CodeCodex

Operate Merv cloud sandboxes safely for expensive, long-running, isolated, GPU, or remote experiment work. Use when provisioning or attaching a sandbox, running commands over SSH, observing durable mervrun receipts, retaining outputs, extending a lease, recovering interrupted execution, or releasing a sandbox.

rapidreview-io/Merv

Skill Claude CodeCodex

Perform a read-only review of a completed Merv task delivery. Verify each Done-when check in the brief against the delivery's evidence — by checking, not by reading — judge whether the checks met mean the goal is achieved, then submit pass, needschanges (back to inprogress), or fail (the task ends).