@yemi33/minions 0.1.1895 → 0.1.1896

package/README.md

@@ -216,8 +216,8 @@ minions work "Explore the codebase and document the architecture"
 
 ## What It Does
 
-- **Auto-discovers work** from plans (`plans/*.json`), pull requests, and work queues across all linked projects
-- **Plan pipeline** — `/plan` spawns a plan agent, chains to plan-to-prd, produces `plans/{project}-{date}.json` with `status: "awaiting-approval"`. Supports shared-branch and parallel strategies.
+- **Auto-discovers work** from plans (`plans/*.md`), pull requests, and work queues across all linked projects (Plans are markdown in `plans/`; PRDs are JSON in `prd/`.)
+- **Plan pipeline** — `/plan` spawns a plan agent, chains to plan-to-prd, produces `plans/{project}-{date}.md` with `status: "awaiting-approval"`. Supports shared-branch and parallel strategies.
 - **Human approval gate** — plans require approval before materializing as work items. Dashboard provides Approve / Discuss & Revise / Reject. Discussion launches an interactive Command Center session via the configured runtime CLI (`config.engine.ccCli`).
 - **Dispatches AI agents** (Claude CLI) with full project context, git worktrees, and MCP server access
 - **Routes intelligently** — fixes first, then reviews, then implementation, matched to agent strengths
@@ -380,7 +380,7 @@ The engine discovers work from 4 sources, in priority order:
 | Priority | Source | Dispatch Type |
 |----------|--------|---------------|
 | 1 | Pull requests (changes-requested, human feedback, build failures, pending review) | `fix`, `review`, `test` |
-| 2 | Plan items (`plans/*.json`, approved) | `implement` |
+| 2 | Plan items (`plans/*.md`, approved) | `implement` |
 | 3 | Per-project work items | item's `type` |
 | 4 | Central work items (project-agnostic tasks) | item's `type` |
 
@@ -699,7 +699,7 @@ To move to a new machine: `npm install -g @yemi33/minions && minions init --forc
   config.json            <- projects[], agents, engine, claude settings (generated by minions init)
   config.template.json   <- Template for new installs
   package.json           <- npm package definition
-  plans/                 <- Approved plans: plans/{project}-{date}.json (generated)
+  plans/                 <- Approved plans: plans/{project}-{date}.md (generated)
   prd/                   <- PRD archives and verification guides (generated)
   pipelines/             <- Pipeline definitions (generated)
   meetings/              <- Meeting state files (generated)

package/engine.js

@@ -4184,7 +4184,7 @@ async function discoverWork(config) {
   }
 
   // Source 2: Minions-level PRD → implements (multi-project, called once outside project loop)
-  // PRD items now flow through plans/*.json → materializePlansAsWorkItems → discoverFromWorkItems
+  // PRD items (prd/*.json), materialized from plans/*.md, flow through materializePlansAsWorkItems → discoverFromWorkItems
 
   // Central work items (project-agnostic — agent decides where to work)
   const centralWork = discoverCentralWorkItems(config);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@yemi33/minions",
-  "version": "0.1.1895",
+  "version": "0.1.1896",
   "description": "Multi-agent AI dev team that runs from ~/.minions/ — five autonomous agents share a single engine, dashboard, and knowledge base",
   "bin": {
     "minions": "bin/minions.js"