@yemi33/minions 0.1.622 → 0.1.624

package/CHANGELOG.md

@@ -1,5 +1,15 @@
 # Changelog
 
+## 0.1.624 (2026-04-08)
+
+### Fixes
+-  reorder implement playbook — build & test before push
+
+## 0.1.623 (2026-04-08)
+
+### Fixes
+-  reorder fix playbook — build & test before push, add build step
+
 ## 0.1.622 (2026-04-08)
 
 ### Fixes

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@yemi33/minions",
-  "version": "0.1.622",
+  "version": "0.1.624",
   "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"

package/playbooks/fix.md

@@ -31,36 +31,38 @@ Use subagents only for genuinely parallel, independent tasks. For sequential wor
 
 2. Fix each issue listed above
 
-3. Commit and push:
-   ```bash
-   git add <specific files>
-   git commit -m "fix: address review feedback on {{pr_id}}"
-   git push
-   ```
+3. Handle merge conflicts if any:
+   - If `git pull` or the PR shows conflicts, resolve them in the worktree
+   - Prefer the PR branch changes, commit the resolution
 
-Do NOT remove the worktree — the engine handles cleanup automatically.
+## Build & Test (MANDATORY before pushing)
 
-## Handling Merge Conflicts
-If you encounter merge conflicts (e.g., during `git pull` or when the PR shows conflicts):
-1. Resolve conflicts in the worktree, preferring the PR branch changes. Commit the resolution.
+Before pushing, verify the fix doesn't break anything:
 
-## Post Response on PR
+1. **Build** the project using its build system (check CLAUDE.md, README, package.json, Makefile). If the build fails, fix it before proceeding.
+2. **Run the full test suite** using whatever command the project specifies (check CLAUDE.md, agent.md, README, or package.json scripts).
+3. If any tests fail due to your changes, fix them before pushing.
+4. If the build fails 3 times, report the errors in your PR comment and stop.
+5. Do NOT push code that breaks existing tests or the build.
 
-{{pr_comment_instructions}}
-- pullRequestId: `{{pr_number}}`
-- content: Explain what was fixed, reference each review finding
-- Sign: `Fixed by Minions ({{agent_name}} — {{agent_role}})`
+## Push & Comment on PR
 
-## Test Validation (MANDATORY before pushing)
+Only after build and tests pass:
 
-Before pushing your fix, run the project's test suite:
+```bash
+git add <specific files>
+git commit -m "fix: address review feedback on {{pr_id}}"
+git push
+```
 
-1. Find the test command by reading the project's own documentation — check CLAUDE.md, agent.md, README, or package.json scripts in the project root. Every project defines its own conventions.
-2. Run the full test suite using whatever command the project specifies
-3. If any tests fail due to your changes, fix them before pushing
-4. Do NOT push code that breaks existing tests
+Do NOT remove the worktree — the engine handles cleanup automatically.
+
+{{pr_comment_instructions}}
+- pullRequestId: `{{pr_number}}`
+- content: Explain what was fixed, reference each review finding, include build/test status
+- Sign: `Fixed by Minions ({{agent_name}} — {{agent_role}})`
 
 ## When to Stop
 
-Your task is complete once you have: (1) pushed the fix, (2) created or updated the PR, and (3) confirmed tests pass. Do NOT continue exploring unrelated code or making additional improvements. Stop immediately after the fix is verified.
+Your task is complete once you have: (1) confirmed build and tests pass, (2) pushed the fix, and (3) commented on the PR. Do NOT continue exploring unrelated code or making additional improvements. Stop immediately.
 

package/playbooks/implement.md

@@ -47,8 +47,27 @@ Use subagents only for genuinely parallel, independent tasks (e.g., editing file
 ## Git Workflow
 
 You are already running in a git worktree on branch `{{branch_name}}`. Do NOT create additional worktrees — the engine pre-created one for you.
+Do NOT remove the worktree — the engine handles cleanup automatically.
+
+## Build & Test (MANDATORY before pushing)
 
-When done:
+After implementation, verify everything works before pushing:
+
+1. **Build** the project using its build system (check CLAUDE.md, package.json, README, Makefile). If the build fails:
+   - Read the error, fix the issue, re-build
+   - If it fails 3 times, report the errors in your findings and stop
+2. **Run the full test suite** using whatever command the project specifies (check CLAUDE.md, agent.md, README, or package.json scripts).
+3. If any tests fail:
+   - Determine if YOUR changes caused the failure
+   - Fix any regressions you introduced
+   - Re-run tests until all pass
+4. If tests were already failing before your changes (pre-existing), note them in the PR description but do NOT block on them
+5. **Run any other checks** the repo defines (linting, type checking, formatting) — read project docs for the full list
+6. Do NOT push code with failing tests or a broken build that you introduced
+
+## Push & Create PR
+
+Only after build and tests pass:
 
 ```bash
 git add <specific files>
@@ -56,36 +75,10 @@ git commit -m "{{commit_message}}"
 git push -u origin {{branch_name}}
 ```
 
-Do NOT remove the worktree — the engine handles cleanup automatically.
-
 {{pr_section}}
 
-## Build and Demo Rule
-
-After implementation:
-1. Build the project using the repo's build system (check CLAUDE.md, package.json, README)
-2. Start if applicable
-3. Include the browser URL and run instructions in the PR description
-
-After building, verify the build succeeded. If the build fails:
-1. Read the error output carefully
-2. Fix the issue
-3. Re-run the build
-4. If it fails 3 times, report the build errors in your findings file and stop
-
-## Test Validation (MANDATORY before PR)
-
-Before creating a PR, run the project's test suite and ensure all existing tests pass:
-
-1. Find the test command by reading the project's own documentation — check CLAUDE.md, agent.md, README, or package.json scripts in the project root. Every project defines its own conventions.
-2. Run the full test suite using whatever command the project specifies
-3. If any tests fail:
-   - Determine if YOUR changes caused the failure (compare with the failing test's assertions)
-   - Fix any regressions you introduced
-   - Re-run tests until all pass
-4. If tests were already failing before your changes (pre-existing failures), note them in the PR description but do NOT block on them
-5. Do NOT create a PR with failing tests that you introduced
+Include build/test status and run instructions in the PR description. If the project has a runnable app, include the localhost URL.
 
 ## When to Stop
 
-Your task is complete once you have: (1) pushed your branch, (2) created the PR, and (3) confirmed the build and tests pass. Do NOT continue exploring, refactoring, or adding features beyond the task description. Stop immediately.
+Your task is complete once you have: (1) confirmed build and tests pass, (2) pushed your branch, and (3) created the PR. Do NOT continue exploring, refactoring, or adding features beyond the task description. Stop immediately.