@yemi33/minions 0.1.714 → 0.1.715

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md CHANGED
@@ -1,5 +1,10 @@
1
1
  # Changelog
2
2
 
3
+ ## 0.1.715 (2026-04-09)
4
+
5
+ ### Features
6
+ - agents must check minions state before starting fresh research
7
+
3
8
  ## 0.1.714 (2026-04-09)
4
9
 
5
10
  ### Other
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@yemi33/minions",
3
- "version": "0.1.714",
3
+ "version": "0.1.715",
4
4
  "description": "Multi-agent AI dev team that runs from ~/.minions/ — five autonomous agents share a single engine, dashboard, and knowledge base",
5
5
  "bin": {
6
6
  "minions": "bin/minions.js"
@@ -4,5 +4,13 @@
4
4
  - Do NOT remove worktrees — the engine handles cleanup automatically.
5
5
  - Do NOT checkout branches in the main working tree — use worktrees or `git diff`/`git show`.
6
6
  - Read `notes.md` for team rules and decisions before starting.
7
+ - **Check minions state before starting fresh.** Before researching from scratch, check what the team already knows:
8
+ - `notes.md` — consolidated team knowledge, decisions, and context
9
+ - `knowledge/` — categorized KB entries (architecture, conventions, build-reports, reviews)
10
+ - `notes/inbox/` — recent agent findings not yet consolidated
11
+ - Previous agent output in `agents/*/live-output.log` for related tasks
12
+ - Work item descriptions and `resultSummary` for prior completed work on the same topic
13
+ - `pinned.md` — critical context flagged by the human teammate
14
+ This avoids duplicating research another agent already completed.
7
15
  - If you discover a repeatable workflow, output it as a ```skill block (the engine auto-extracts it).
8
16
  - Do TDD where it makes sense — write failing tests first, then implement, then verify tests pass. Especially for bug fixes (write a test that reproduces the bug) and new utility functions.