Improve a document through editorial review by four distinguished editors: FT, The Economist, London Review of Books, and The New Yorker. Uses a ruflo hive-mind where each editor reviews independently, then they debate and synthesize recommendations. Use when the user says "masthead", "editorial review", "improve this document", "make this publishable", or wants rigorous multi-perspective editorial feedback on prose.
Four editors from elite publications review a document independently, debate their perspectives, and produce a unified set of recommendations (or articulated tradeoffs). After review with you, they incorporate the feedback into the document.
/masthead <path-to-document>
/masthead <path-to-document> --voice=ft|economist|lrb|newyorker
--voice=<masthead>: After the collaborative review, optimise the final rewrite for a
specific publication's voice. If omitted, editors agree on the best target voice for the piece.Each editor brings a distinct tradition. See references/editor-personas.md for full details.
| Editor | Publication | Signature |
|---|---|---|
| FT Editor | Financial Times | Precision, authority, global scope. Values concision and clarity over literary flourish. Every sentence must earn its place. Suspicious of jargon, allergic to padding. |
| Economist Editor | The Economist | Institutional voice, wit, argument-driven. Sentences should do work. Ruthlessly compress. If a paragraph can be a sentence, make it one. Loves a well-turned phrase but never at the expense of meaning. |
| LRB Editor | London Review of Books | Essayistic depth, intellectual range, tolerance for digression when it illuminates. Cares about rhythm, texture, the quality of attention a piece demands. Suspicious of false authority and received opinion. |
| New Yorker Editor | The New Yorker | Narrative craft, rigorous fact-grounding, elegant structure. Obsessive about clarity and the reader's experience. Will restructure a piece entirely if the arc doesn't work. Comma usage is a moral question. |
All four editors share these commitments:
Read the document. Identify:
Store in hive-mind shared memory for all editors to reference.
mcp__ruflo__hive-mind_init(queenId: "masthead-queen", topology: "mesh")
Spawn four specialist editors:
mcp__ruflo__hive-mind_spawn(count: 1, agentType: "specialist", prefix: "ed-ft", role: "specialist")
mcp__ruflo__hive-mind_spawn(count: 1, agentType: "specialist", prefix: "ed-economist", role: "specialist")
mcp__ruflo__hive-mind_spawn(count: 1, agentType: "specialist", prefix: "ed-lrb", role: "specialist")
mcp__ruflo__hive-mind_spawn(count: 1, agentType: "specialist", prefix: "ed-newyorker", role: "specialist")
Store the document content and analysis in shared memory:
mcp__ruflo__hive-mind_memory(action: "set", key: "document-text", value: "<full document>")
mcp__ruflo__hive-mind_memory(action: "set", key: "document-analysis", value: "<genre, audience, word count, initial observations>")
Each editor reviews the document from their publication's perspective. Run all four reviews in parallel using the Agent tool. Each agent should:
references/editor-personas.md)mcp__ruflo__hive-mind_memory(action: "set", key: "review-ft", value: "<FT editor's review>")
mcp__ruflo__hive-mind_memory(action: "set", key: "review-economist", value: "<Economist editor's review>")
mcp__ruflo__hive-mind_memory(action: "set", key: "review-lrb", value: "<LRB editor's review>")
mcp__ruflo__hive-mind_memory(action: "set", key: "review-newyorker", value: "<New Yorker editor's review>")
Each review must address:
Broadcast all four reviews to the hive-mind so each editor can see the others' perspectives:
mcp__ruflo__hive-mind_broadcast(
message: "All reviews are in. Each editor should now read the other three reviews and prepare their positions for debate.",
priority: "high"
)
Simulate a structured editorial debate. The editors should:
Use the consensus mechanism for firm recommendations:
mcp__ruflo__hive-mind_consensus(action: "propose", type: "editorial-recommendation", value: "<recommendation>")
Each editor votes. Recommendations with unanimous support become "consensus recommendations." Those with majority support become "majority recommendations." Dissents are recorded with reasoning.
Store the debate output:
mcp__ruflo__hive-mind_memory(action: "set", key: "debate-consensus", value: "<consensus recommendations>")
mcp__ruflo__hive-mind_memory(action: "set", key: "debate-tradeoffs", value: "<articulated tradeoffs>")
mcp__ruflo__hive-mind_memory(action: "set", key: "debate-priorities", value: "<top 3 highest-impact changes>")
Present the editorial findings to the user in this structure:
# Masthead Editorial Review
**Document:** <name>
**Genre:** <genre> | **Audience:** <audience> | **Word count:** <approx>
## Top 3 Priorities
<The three highest-impact changes, ranked>
## Consensus Recommendations
<Changes all four editors agree on — these are strong signals>
## Majority Recommendations
<Changes 3 of 4 editors support, with the dissenting view noted>
## Editorial Tradeoffs
<Genuine tensions where the right answer depends on what kind of piece this wants to be>
## Emdash Report
<Every emdash in the document, with the recommended replacement>
## Per-Editor Notes
<Any distinctive insight from a single editor that didn't surface in debate but is worth considering>
Stop here and wait for the user's feedback. Ask which recommendations to accept, which to reject, and whether they have a preference for the target voice.
Based on the user's direction:
After writing, present a brief summary of changes made.
mcp__ruflo__hive-mind_shutdown(graceful: true)