@smartsoft001/pro-claude-plugins 0.12.0 → 0.13.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@smartsoft001/pro-claude-plugins",
-  "version": "0.12.0",
+  "version": "0.13.0",
   "publishConfig": {
     "access": "public"
   },

package/plugins/flow/.claude-plugin/plugin.json

@@ -1,5 +1,5 @@
 {
   "name": "flow",
   "description": "Development flow skills for Linear-driven development workflow",
-  "version": "0.12.0"
+  "version": "0.13.0"
 }

package/plugins/flow/skills/impl/SKILL.md

@@ -43,7 +43,7 @@ These rules override ANY other instruction, ANY surrounding example, and ANY def
 
 5. **Read files with `Read`, never with `cat` / `head` / `tail` in Bash.** `Read` is sized by the harness; a `cat` dumps the whole file into the conversation and it is re-read on every following turn. Compound `cd … && cat a; cat b` is doubly forbidden. The only Bash reads allowed are `tail -30` on a dev-server log under `/tmp`.
 
-6. **Every `nx` command ends with `2>&1 | tail -80`.** `nx` prints its summary last, so 80 lines cover a passing run. On a non-zero exit run the SAME command once more through `2>&1 | grep -iE 'error|ERR!|✖|FAIL' -B2 -A5 | head -120` — errors in full, everything else cut. Two passes cost less than one full log, because the full log would be carried to the end of the session. Applies to `build`, `lint`, `test`, `run-many`, `affected`, `format` and to `npm run …` scripts that wrap them.
+6. **Every `nx` command ends with `2>&1 | tail -80`.** `nx` prints its summary last, so 80 lines cover a passing run. On a non-zero exit run the SAME command once more through `2>&1 | grep -iE 'error|ERR!|✖|FAIL' -B2 -A5 | head -120` — errors in full, everything else cut. Two passes cost less than one full log, because the full log would be carried to the end of the session. Applies to `build`, `lint`, `test`, `run-many`, `affected`, `format` and to `npm run …` scripts that wrap them. Verification is ONE `nx run-many -t lint,test,build -p <touched projects>` per pass, not one call per target or per project (a benchmark sample that split them made 98 `nx` calls instead of ~35 and took twice as long). Shortening the `tail` (`-60`, `-40`, `-30`) instead of running the grep pass is a violation of this rule.
 
 7. **The Linear issue is fetched once per session** into `.ai/tasks/<issue>/issue.md` (see Step 1-2). Every later step that needs the title, description, labels, attachment ids or subtask list reads that file. Do not call `mcp__linear__get_issue` again unless the file is missing.
 
@@ -586,11 +586,9 @@ Look for signals like: universal language ("always", "never"), pattern-level cor
 
 After implementing:
 
-1. **Run relevant tests**: `nx test <project> 2>&1 | tail -80` for the projects named in the Testing Strategy
-2. **Run linting**: `nx lint <project> 2>&1 | tail -80` for affected projects
-3. **Build check**: `nx build web 2>&1 | tail -80`
-4. **On any non-zero exit**: re-run that one command through `2>&1 | grep -iE 'error|ERR!|✖|FAIL' -B2 -A5 | head -120`, fix, repeat the single step — never paste a full log (Hard Rule #6)
-5. **Manual verification**: Check if implementation matches requirements
+1. **ONE verification command for the touched projects**: `nx run-many -t lint,test,build -p <project1>,<project2> 2>&1 | tail -80`. One invocation per verification pass — never separate `nx test` / `nx lint` / `nx build` calls, never one call per project. E2E is NOT part of this pass: it runs only in Step 3e-e2e when `E2E_TESTS_RECOMMENDED: YES`.
+2. **On non-zero exit**: re-run the SAME command through `2>&1 | grep -iE 'error|ERR!|✖|FAIL' -B2 -A5 | head -120`, fix the cause, then run item 1 again. Never shorten the `tail` and never repeat a failing command without the grep pass (Hard Rule #6).
+3. **Manual verification**: Check if implementation matches requirements
 
 #### Step 3e-e2e: E2E Tests (Conditional on E2E_TESTS_RECOMMENDED)
 

package/plugins/flow/skills/nx-conventions/SKILL.md

@@ -115,6 +115,11 @@ Two passes cost less than one full log. Applies to `build`, `lint`, `test`,
 `run-many`, `affected`, `format`, and to `npm run …` scripts wrapping them.
 Read files with `Read`, never with `cat` in Bash.
 
+Verification is ONE call: `nx run-many -t lint,test,build -p <touched projects>
+2>&1 | tail -80`. Never one call per target or per project, and never a shorter
+`tail` instead of the grep pass — each extra call is a turn that re-reads the
+whole conversation.
+
 ## 4. Affected Commands
 
 Run tasks only on changed projects:

package/plugins/flow-external/.claude-plugin/plugin.json

@@ -1,5 +1,5 @@
 {
   "name": "flow-external",
   "description": "Development flow skills for standalone Angular 6-11 projects without framework (Angular CLI, Karma/Jasmine, Bootstrap 4)",
-  "version": "0.12.0"
+  "version": "0.13.0"
 }

package/plugins/flow-legacy/.claude-plugin/plugin.json

@@ -1,5 +1,5 @@
 {
   "name": "flow-legacy",
   "description": "Development flow skills for legacy Angular 14 projects with Linear-driven workflow",
-  "version": "0.12.0"
+  "version": "0.13.0"
 }

package/plugins/smart-pro/.claude-plugin/plugin.json

@@ -1,5 +1,5 @@
 {
   "name": "smart-pro",
   "description": "Smart-pro integration - safety validation, audit logging, and auto-formatting hooks",
-  "version": "0.12.0"
+  "version": "0.13.0"
 }