Two-agent editing loop: an editor applies five named schemata, an evaluator scores blind before reading the editor's trace, and they loop until the text passes.
0 on GitHubby Alastair Zevedv0.3.0MITupdated 1 month agoWriting
/
Plugin editorial-recension from marketplace editorial-recension in AlastairZeved/Editorial-Recension. Commands read from the repo's manifest — 1 month ago.
What it installs
Skills (1)
editorial-recension
Use when editing prose, essays, guides, or any writing meant to carry a reader through a reasoning chain — especially cross-domain writing where the author has expertise the reader does not
Subagents (2)
editor
Editorial agent whose identity is the editing loop itself — applies five named schemata (Barrier Bridge, Chain Repair, Compression Pass, Flow Weld, Ripple Read) in phased execution and returns edited text plus a schema trace. Invoked by the editorial-recension skill after editorial context is confir
evaluator
Adversarial verification agent — scores editor output independently against the measurable feature set BEFORE reading the editor's trace, then confirms or rejects the termination condition. Does not edit, does not suggest rewrites. Invoked by the editorial-recension skill after each editor pass.
AgentDB (external: maintained in ruvnet/agentdb, pinned to commit 27678c3, plugin 3.6.0): agentdb's own standalone MCP server pinned to [email protected] (vector memory with get/list/update/delete for records, patterns and skills, hybrid keyword + vector episode search and an opt-in local cross-encoder, an opt-in aidefence injection guard on memory writes, reflexion, skills, outcome feedback, capabilities report), a memory-specialist agent, 3 skills, /agentdb-status, and the agentdb mod guard that keeps secrets out of memory and refuses delete/reset unless allowed. Complements ruflo-agentdb, which reaches AgentDB through ruflo's server
Connect Claude Code directly to your CockroachDB clusters for hands-on database work — explore schemas, write optimized SQL, debug queries, and manage distributed database clusters. This plugin provides 14 tools across two active MCP backends (self-hosted MCP Toolbox and managed CockroachDB Cloud MCP Server), three specialized agents (DBA, Developer, Operator), 32 skills across 6 operational domains, and built-in safety hooks.
Provision direct cloud access (Vertex AI, Bedrock, or LLM gateway) for the Claude Microsoft 365 add-in. Generates the customized manifest, walks through Azure admin consent, and writes per-user config via Graph extension attributes.
1 skill · 9 commands
anthropics/financial-services 41,259
Maintain editorial-recension?
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.