@codyswann/lisa 4.35.4 → 4.35.5

package/package.json

@@ -166,7 +166,7 @@
     "zod-validation-error": "^4.0.0"
   },
   "name": "@codyswann/lisa",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "Claude Code governance framework that applies guardrails, guidance, and automated enforcement to projects",
   "main": "dist/index.js",
   "exports": {
@@ -314,7 +314,7 @@
     "test": "tests"
   },
   "types": "./dist/index.d.ts",
-  "lisaReleaseCommit": "cdfd50ffb82cb4a61189aa88ac5079f7191d5af3",
-  "gitHead": "cdfd50ffb82cb4a61189aa88ac5079f7191d5af3",
-  "lisaReleaseTag": "v4.35.4"
+  "lisaReleaseCommit": "eef625a21fce4a478796cb76926a3c8e03d032b6",
+  "gitHead": "eef625a21fce4a478796cb76926a3c8e03d032b6",
+  "lisaReleaseTag": "v4.35.5"
 }

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

@@ -1,6 +1,6 @@
 {
   "name": "lisa",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "Universal governance — agents, skills, commands, hooks, and rules for all projects",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "Universal governance: agents, skills, commands, hooks, and rules for all projects.",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa/.codex-plugin/skills/lisa-jsdoc-best-practices/SKILL.md

@@ -348,7 +348,66 @@ In `@example` blocks, use fenced code blocks and escape `@` as `\@`:
  */
 ```
 
-### Quick Reference for Escaping
+### Path Examples Must Not Contain the Block Terminator
+
+A path written as an example inside a doc comment **ends the comment** if it
+contains `*/` — a glob such as `sandbox-*/`, or any real directory whose
+name ends in an asterisk. Everything below that point is then parsed as source:
+path segments become identifiers, and the separator between them becomes
+division.
+
+**Write the wildcard as a placeholder, not a glob:**
+
+```typescript
+// WRONG — the comment ends inside the path, mid-line
+/**
+ * Debris lands at `.stryker-tmp/bite-guard-intact/sandbox-*/rails/scripts/foo.sh`
+ * and this line is no longer a comment.
+ */
+
+// RIGHT — a placeholder cannot terminate the block
+/**
+ * Debris lands at `.stryker-tmp/bite-guard-intact/sandbox-<id>/rails/scripts/foo.sh`
+ * and this line is still a comment.
+ */
+```
+
+`<id>`, `<name>`, `<n>` — the same placeholder convention used everywhere else
+in Lisa's docs. Escaping (`*\/`) also works but produces an example nobody can
+copy and paste, which defeats the point of writing one.
+
+### What it looks like when you get it wrong
+
+The build goes red immediately — `bun run typecheck`, `bun run lint` and the
+test run all fail — but **none of them mentions a comment**, and every line
+they report sits *below* the real cause. Measured, with the true cause on
+line 89:
+
+```text
+src/configs/repo-scan.ts(90,9):  error TS1005: ';' expected.
+src/configs/repo-scan.ts(90,20): error TS1443: Module declaration names may only use ' or " quoted strings.
+src/configs/repo-scan.ts(94,1):  error TS1160: Unterminated template literal.
+```
+
+Errors naming identifiers you never wrote — `Cannot find name 'mutation'`,
+`Cannot find name 'src'` — are the giveaway: those are backtick contents from
+inside the comment, now being read as code. **Look upward for a doc comment
+before looking for a missing import.**
+
+Lisa's gate runner says this for you. When a gate fails, it scans the files the
+failure named and reports the closed comment by name:
+
+```text
+a doc comment in src/configs/repo-scan.ts ends early, on line 89 — every error
+reported below that line is downstream of it, not a fault of its own
+  ↳ src/configs/repo-scan.ts:89 — the block opened on line 87 ends at the
+    terminator INSIDE this line, not on line 92
+```
+
+It is a text scan rather than a lint rule on purpose: the file does not parse,
+so ESLint reports `Parsing error` and runs zero rules on it.
+
+## Quick Reference for Escaping
 
 | Context | Approach | Example |
 |---------|----------|---------|

package/plugins/lisa/rules/reference/measurement-integrity.md

@@ -33,6 +33,16 @@ An entire corpus sits outside the query's scope and nothing says so. `gh search
 
 **Catch it:** validate the detector against known-true items before believing any count.
 
+#### A second domain, which is what makes this a category rather than a quirk
+
+The same mode, on a filesystem rather than a tracker. A survey of agent worktrees enumerating `.claude/worktrees/` and `.worktrees/` returns a well-formed list — and omits every worktree created outside the repository tree, under the per-user temporary directory. Four such worktrees existed, three of them with uncommitted changes; none appeared.
+
+Run it through the membership test and it qualifies on all three counts: the list is **well formed** (no error, no warning, no partial marker); the omission is **invisible from the list itself**, which looks exactly like a complete survey of a machine with fewer worktrees on it; and **a mechanical step would have caught it** — the same one A1 already prescribes, validating the enumeration against a worktree you know exists.
+
+This example is here rather than folded into the paragraph above because **a second domain tests whether the category is real or just a description of one tool's behaviour.** A mode observed only through `gh search` could be a fact about GitHub's search semantics; the same shape in a `find` over directories says the failure belongs to *enumeration with an unstated boundary*, whichever substrate is enumerating. When extending this document, a new domain for an existing mode is worth as much as a new mode.
+
+**The consequence in that instance was not academic.** Uncommitted work outside the repository tree is invisible to every query anyone would run before deciding what to clean up, and looks identical to abandoned scratch — so a survey feeding a deletion decision under-reports precisely the thing that must not be deleted. See the worktree-and-binding hazards for the separate question of a mitigation whose cost is invisibility; the measurement half is this mode.
+
 ### A2. Truncation — under, enumeration
 
 Real members past the first page are dropped with no truncation signal. `gh issue list` and `gh pr list` default to 30 and cap silently at whatever `--limit` is passed: one audit reported **37 items where the answer was 513**, a 14× undercount. A paging API returning **249 of 845 rows with `hasNextPage: false`** is the same mode on another substrate.

package/plugins/lisa/skills/lisa-jsdoc-best-practices/SKILL.md

@@ -348,7 +348,66 @@ In `@example` blocks, use fenced code blocks and escape `@` as `\@`:
  */
 ```
 
-### Quick Reference for Escaping
+### Path Examples Must Not Contain the Block Terminator
+
+A path written as an example inside a doc comment **ends the comment** if it
+contains `*/` — a glob such as `sandbox-*/`, or any real directory whose
+name ends in an asterisk. Everything below that point is then parsed as source:
+path segments become identifiers, and the separator between them becomes
+division.
+
+**Write the wildcard as a placeholder, not a glob:**
+
+```typescript
+// WRONG — the comment ends inside the path, mid-line
+/**
+ * Debris lands at `.stryker-tmp/bite-guard-intact/sandbox-*/rails/scripts/foo.sh`
+ * and this line is no longer a comment.
+ */
+
+// RIGHT — a placeholder cannot terminate the block
+/**
+ * Debris lands at `.stryker-tmp/bite-guard-intact/sandbox-<id>/rails/scripts/foo.sh`
+ * and this line is still a comment.
+ */
+```
+
+`<id>`, `<name>`, `<n>` — the same placeholder convention used everywhere else
+in Lisa's docs. Escaping (`*\/`) also works but produces an example nobody can
+copy and paste, which defeats the point of writing one.
+
+### What it looks like when you get it wrong
+
+The build goes red immediately — `bun run typecheck`, `bun run lint` and the
+test run all fail — but **none of them mentions a comment**, and every line
+they report sits *below* the real cause. Measured, with the true cause on
+line 89:
+
+```text
+src/configs/repo-scan.ts(90,9):  error TS1005: ';' expected.
+src/configs/repo-scan.ts(90,20): error TS1443: Module declaration names may only use ' or " quoted strings.
+src/configs/repo-scan.ts(94,1):  error TS1160: Unterminated template literal.
+```
+
+Errors naming identifiers you never wrote — `Cannot find name 'mutation'`,
+`Cannot find name 'src'` — are the giveaway: those are backtick contents from
+inside the comment, now being read as code. **Look upward for a doc comment
+before looking for a missing import.**
+
+Lisa's gate runner says this for you. When a gate fails, it scans the files the
+failure named and reports the closed comment by name:
+
+```text
+a doc comment in src/configs/repo-scan.ts ends early, on line 89 — every error
+reported below that line is downstream of it, not a fault of its own
+  ↳ src/configs/repo-scan.ts:89 — the block opened on line 87 ends at the
+    terminator INSIDE this line, not on line 92
+```
+
+It is a text scan rather than a lint rule on purpose: the file does not parse,
+so ESLint reports `Parsing error` and runs zero rules on it.
+
+## Quick Reference for Escaping
 
 | Context | Approach | Example |
 |---------|----------|---------|

package/plugins/lisa-agy/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "Universal governance — agents, skills, commands, hooks, and rules for all projects",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-agy/skills/lisa-jsdoc-best-practices/SKILL.md

@@ -348,7 +348,66 @@ In `@example` blocks, use fenced code blocks and escape `@` as `\@`:
  */
 ```
 
-### Quick Reference for Escaping
+### Path Examples Must Not Contain the Block Terminator
+
+A path written as an example inside a doc comment **ends the comment** if it
+contains `*/` — a glob such as `sandbox-*/`, or any real directory whose
+name ends in an asterisk. Everything below that point is then parsed as source:
+path segments become identifiers, and the separator between them becomes
+division.
+
+**Write the wildcard as a placeholder, not a glob:**
+
+```typescript
+// WRONG — the comment ends inside the path, mid-line
+/**
+ * Debris lands at `.stryker-tmp/bite-guard-intact/sandbox-*/rails/scripts/foo.sh`
+ * and this line is no longer a comment.
+ */
+
+// RIGHT — a placeholder cannot terminate the block
+/**
+ * Debris lands at `.stryker-tmp/bite-guard-intact/sandbox-<id>/rails/scripts/foo.sh`
+ * and this line is still a comment.
+ */
+```
+
+`<id>`, `<name>`, `<n>` — the same placeholder convention used everywhere else
+in Lisa's docs. Escaping (`*\/`) also works but produces an example nobody can
+copy and paste, which defeats the point of writing one.
+
+### What it looks like when you get it wrong
+
+The build goes red immediately — `bun run typecheck`, `bun run lint` and the
+test run all fail — but **none of them mentions a comment**, and every line
+they report sits *below* the real cause. Measured, with the true cause on
+line 89:
+
+```text
+src/configs/repo-scan.ts(90,9):  error TS1005: ';' expected.
+src/configs/repo-scan.ts(90,20): error TS1443: Module declaration names may only use ' or " quoted strings.
+src/configs/repo-scan.ts(94,1):  error TS1160: Unterminated template literal.
+```
+
+Errors naming identifiers you never wrote — `Cannot find name 'mutation'`,
+`Cannot find name 'src'` — are the giveaway: those are backtick contents from
+inside the comment, now being read as code. **Look upward for a doc comment
+before looking for a missing import.**
+
+Lisa's gate runner says this for you. When a gate fails, it scans the files the
+failure named and reports the closed comment by name:
+
+```text
+a doc comment in src/configs/repo-scan.ts ends early, on line 89 — every error
+reported below that line is downstream of it, not a fault of its own
+  ↳ src/configs/repo-scan.ts:89 — the block opened on line 87 ends at the
+    terminator INSIDE this line, not on line 92
+```
+
+It is a text scan rather than a lint rule on purpose: the file does not parse,
+so ESLint reports `Parsing error` and runs zero rules on it.
+
+## Quick Reference for Escaping
 
 | Context | Approach | Example |
 |---------|----------|---------|

package/plugins/lisa-cdk/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-cdk",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "AWS CDK-specific plugin",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-cdk/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-cdk",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "AWS CDK-specific Lisa plugin.",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-cdk-agy/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-cdk",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "AWS CDK-specific plugin",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-cdk-copilot/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-cdk",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "AWS CDK-specific plugin",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-cdk-cursor/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-cdk",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "AWS CDK-specific plugin",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-copilot/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "Universal governance — agents, skills, commands, hooks, and rules for all projects",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-copilot/rules/reference/measurement-integrity.md

@@ -33,6 +33,16 @@ An entire corpus sits outside the query's scope and nothing says so. `gh search
 
 **Catch it:** validate the detector against known-true items before believing any count.
 
+#### A second domain, which is what makes this a category rather than a quirk
+
+The same mode, on a filesystem rather than a tracker. A survey of agent worktrees enumerating `.claude/worktrees/` and `.worktrees/` returns a well-formed list — and omits every worktree created outside the repository tree, under the per-user temporary directory. Four such worktrees existed, three of them with uncommitted changes; none appeared.
+
+Run it through the membership test and it qualifies on all three counts: the list is **well formed** (no error, no warning, no partial marker); the omission is **invisible from the list itself**, which looks exactly like a complete survey of a machine with fewer worktrees on it; and **a mechanical step would have caught it** — the same one A1 already prescribes, validating the enumeration against a worktree you know exists.
+
+This example is here rather than folded into the paragraph above because **a second domain tests whether the category is real or just a description of one tool's behaviour.** A mode observed only through `gh search` could be a fact about GitHub's search semantics; the same shape in a `find` over directories says the failure belongs to *enumeration with an unstated boundary*, whichever substrate is enumerating. When extending this document, a new domain for an existing mode is worth as much as a new mode.
+
+**The consequence in that instance was not academic.** Uncommitted work outside the repository tree is invisible to every query anyone would run before deciding what to clean up, and looks identical to abandoned scratch — so a survey feeding a deletion decision under-reports precisely the thing that must not be deleted. See the worktree-and-binding hazards for the separate question of a mitigation whose cost is invisibility; the measurement half is this mode.
+
 ### A2. Truncation — under, enumeration
 
 Real members past the first page are dropped with no truncation signal. `gh issue list` and `gh pr list` default to 30 and cap silently at whatever `--limit` is passed: one audit reported **37 items where the answer was 513**, a 14× undercount. A paging API returning **249 of 845 rows with `hasNextPage: false`** is the same mode on another substrate.

package/plugins/lisa-copilot/skills/lisa-jsdoc-best-practices/SKILL.md

@@ -348,7 +348,66 @@ In `@example` blocks, use fenced code blocks and escape `@` as `\@`:
  */
 ```
 
-### Quick Reference for Escaping
+### Path Examples Must Not Contain the Block Terminator
+
+A path written as an example inside a doc comment **ends the comment** if it
+contains `*/` — a glob such as `sandbox-*/`, or any real directory whose
+name ends in an asterisk. Everything below that point is then parsed as source:
+path segments become identifiers, and the separator between them becomes
+division.
+
+**Write the wildcard as a placeholder, not a glob:**
+
+```typescript
+// WRONG — the comment ends inside the path, mid-line
+/**
+ * Debris lands at `.stryker-tmp/bite-guard-intact/sandbox-*/rails/scripts/foo.sh`
+ * and this line is no longer a comment.
+ */
+
+// RIGHT — a placeholder cannot terminate the block
+/**
+ * Debris lands at `.stryker-tmp/bite-guard-intact/sandbox-<id>/rails/scripts/foo.sh`
+ * and this line is still a comment.
+ */
+```
+
+`<id>`, `<name>`, `<n>` — the same placeholder convention used everywhere else
+in Lisa's docs. Escaping (`*\/`) also works but produces an example nobody can
+copy and paste, which defeats the point of writing one.
+
+### What it looks like when you get it wrong
+
+The build goes red immediately — `bun run typecheck`, `bun run lint` and the
+test run all fail — but **none of them mentions a comment**, and every line
+they report sits *below* the real cause. Measured, with the true cause on
+line 89:
+
+```text
+src/configs/repo-scan.ts(90,9):  error TS1005: ';' expected.
+src/configs/repo-scan.ts(90,20): error TS1443: Module declaration names may only use ' or " quoted strings.
+src/configs/repo-scan.ts(94,1):  error TS1160: Unterminated template literal.
+```
+
+Errors naming identifiers you never wrote — `Cannot find name 'mutation'`,
+`Cannot find name 'src'` — are the giveaway: those are backtick contents from
+inside the comment, now being read as code. **Look upward for a doc comment
+before looking for a missing import.**
+
+Lisa's gate runner says this for you. When a gate fails, it scans the files the
+failure named and reports the closed comment by name:
+
+```text
+a doc comment in src/configs/repo-scan.ts ends early, on line 89 — every error
+reported below that line is downstream of it, not a fault of its own
+  ↳ src/configs/repo-scan.ts:89 — the block opened on line 87 ends at the
+    terminator INSIDE this line, not on line 92
+```
+
+It is a text scan rather than a lint rule on purpose: the file does not parse,
+so ESLint reports `Parsing error` and runs zero rules on it.
+
+## Quick Reference for Escaping
 
 | Context | Approach | Example |
 |---------|----------|---------|

package/plugins/lisa-cursor/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "Universal governance — agents, skills, commands, hooks, and rules for all projects",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-cursor/rules/measurement-integrity-reference.mdc

@@ -38,6 +38,16 @@ An entire corpus sits outside the query's scope and nothing says so. `gh search
 
 **Catch it:** validate the detector against known-true items before believing any count.
 
+#### A second domain, which is what makes this a category rather than a quirk
+
+The same mode, on a filesystem rather than a tracker. A survey of agent worktrees enumerating `.claude/worktrees/` and `.worktrees/` returns a well-formed list — and omits every worktree created outside the repository tree, under the per-user temporary directory. Four such worktrees existed, three of them with uncommitted changes; none appeared.
+
+Run it through the membership test and it qualifies on all three counts: the list is **well formed** (no error, no warning, no partial marker); the omission is **invisible from the list itself**, which looks exactly like a complete survey of a machine with fewer worktrees on it; and **a mechanical step would have caught it** — the same one A1 already prescribes, validating the enumeration against a worktree you know exists.
+
+This example is here rather than folded into the paragraph above because **a second domain tests whether the category is real or just a description of one tool's behaviour.** A mode observed only through `gh search` could be a fact about GitHub's search semantics; the same shape in a `find` over directories says the failure belongs to *enumeration with an unstated boundary*, whichever substrate is enumerating. When extending this document, a new domain for an existing mode is worth as much as a new mode.
+
+**The consequence in that instance was not academic.** Uncommitted work outside the repository tree is invisible to every query anyone would run before deciding what to clean up, and looks identical to abandoned scratch — so a survey feeding a deletion decision under-reports precisely the thing that must not be deleted. See the worktree-and-binding hazards for the separate question of a mitigation whose cost is invisibility; the measurement half is this mode.
+
 ### A2. Truncation — under, enumeration
 
 Real members past the first page are dropped with no truncation signal. `gh issue list` and `gh pr list` default to 30 and cap silently at whatever `--limit` is passed: one audit reported **37 items where the answer was 513**, a 14× undercount. A paging API returning **249 of 845 rows with `hasNextPage: false`** is the same mode on another substrate.

package/plugins/lisa-cursor/skills/lisa-jsdoc-best-practices/SKILL.md

@@ -348,7 +348,66 @@ In `@example` blocks, use fenced code blocks and escape `@` as `\@`:
  */
 ```
 
-### Quick Reference for Escaping
+### Path Examples Must Not Contain the Block Terminator
+
+A path written as an example inside a doc comment **ends the comment** if it
+contains `*/` — a glob such as `sandbox-*/`, or any real directory whose
+name ends in an asterisk. Everything below that point is then parsed as source:
+path segments become identifiers, and the separator between them becomes
+division.
+
+**Write the wildcard as a placeholder, not a glob:**
+
+```typescript
+// WRONG — the comment ends inside the path, mid-line
+/**
+ * Debris lands at `.stryker-tmp/bite-guard-intact/sandbox-*/rails/scripts/foo.sh`
+ * and this line is no longer a comment.
+ */
+
+// RIGHT — a placeholder cannot terminate the block
+/**
+ * Debris lands at `.stryker-tmp/bite-guard-intact/sandbox-<id>/rails/scripts/foo.sh`
+ * and this line is still a comment.
+ */
+```
+
+`<id>`, `<name>`, `<n>` — the same placeholder convention used everywhere else
+in Lisa's docs. Escaping (`*\/`) also works but produces an example nobody can
+copy and paste, which defeats the point of writing one.
+
+### What it looks like when you get it wrong
+
+The build goes red immediately — `bun run typecheck`, `bun run lint` and the
+test run all fail — but **none of them mentions a comment**, and every line
+they report sits *below* the real cause. Measured, with the true cause on
+line 89:
+
+```text
+src/configs/repo-scan.ts(90,9):  error TS1005: ';' expected.
+src/configs/repo-scan.ts(90,20): error TS1443: Module declaration names may only use ' or " quoted strings.
+src/configs/repo-scan.ts(94,1):  error TS1160: Unterminated template literal.
+```
+
+Errors naming identifiers you never wrote — `Cannot find name 'mutation'`,
+`Cannot find name 'src'` — are the giveaway: those are backtick contents from
+inside the comment, now being read as code. **Look upward for a doc comment
+before looking for a missing import.**
+
+Lisa's gate runner says this for you. When a gate fails, it scans the files the
+failure named and reports the closed comment by name:
+
+```text
+a doc comment in src/configs/repo-scan.ts ends early, on line 89 — every error
+reported below that line is downstream of it, not a fault of its own
+  ↳ src/configs/repo-scan.ts:89 — the block opened on line 87 ends at the
+    terminator INSIDE this line, not on line 92
+```
+
+It is a text scan rather than a lint rule on purpose: the file does not parse,
+so ESLint reports `Parsing error` and runs zero rules on it.
+
+## Quick Reference for Escaping
 
 | Context | Approach | Example |
 |---------|----------|---------|

package/plugins/lisa-expo/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-expo",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "Expo/React Native-specific skills, agents, rules, and MCP servers",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-expo/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-expo",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "Expo and React Native-specific skills, agents, rules, and MCP servers.",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-expo-agy/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-expo",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "Expo/React Native-specific skills, agents, rules, and MCP servers",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-expo-copilot/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-expo",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "Expo/React Native-specific skills, agents, rules, and MCP servers",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-expo-cursor/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-expo",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "Expo/React Native-specific skills, agents, rules, and MCP servers",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-harper-fabric/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-harper-fabric",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "Harper/Fabric-specific rules for TypeScript component apps",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-harper-fabric/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-harper-fabric",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "Harper/Fabric-specific Lisa rules for TypeScript component apps.",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-harper-fabric-agy/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-harper-fabric",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "Harper/Fabric-specific rules for TypeScript component apps",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-harper-fabric-copilot/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-harper-fabric",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "Harper/Fabric-specific rules for TypeScript component apps",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-harper-fabric-cursor/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-harper-fabric",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "Harper/Fabric-specific rules for TypeScript component apps",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-nestjs/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-nestjs",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "NestJS-specific skills (GraphQL, TypeORM) and hooks (migration write-protection)",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-nestjs/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-nestjs",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "NestJS-specific skills and migration write-protection hooks.",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-nestjs-agy/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-nestjs",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "NestJS-specific skills (GraphQL, TypeORM) and hooks (migration write-protection)",
   "author": {
     "name": "Cody Swann"

package/plugins/lisa-nestjs-copilot/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-nestjs",
-  "version": "4.35.4",
+  "version": "4.35.5",
   "description": "NestJS-specific skills (GraphQL, TypeORM) and hooks (migration write-protection)",
   "author": {
     "name": "Cody Swann"