milens 0.7.2 → 0.7.3

package/.agents/skills/parser/SKILL.md

@@ -1,86 +1,86 @@
----
-generated-by: milens
-name: milens-parser
-description: Code intelligence for the parser area — symbols, dependencies, and entry points
----
-
-<!-- Generated by milens — safe to delete/regenerate -->
-# Parser
-
-## Working with this area
-When working with code in **parser/**, follow these mandatory safety rules:
-
-### Before editing any symbol in this area:
-1. Call `mcp_milens_impact({target: "<symbol>", repo: "<workspaceRoot>"})` — check blast radius
-2. If depth-1 dependents > 5 → **STOP and warn** before proceeding
-3. Call `mcp_milens_context({name: "<symbol>", repo: "<workspaceRoot>"})` — see all callers/callees
-
-### Before committing changes in this area:
-1. Call `mcp_milens_detect_changes({repo: "<workspaceRoot>"})` — verify scope
-2. If unexpected files changed → **STOP and report**
-
-### Key tools for this area:
-| Task | Tool |
-|---|---|
-| Find all references | `mcp_milens_context` |
-| Check edit safety | `mcp_milens_edit_check` |
-| Text search across files | `mcp_milens_grep` |
-| See file symbols | `mcp_milens_get_file_symbols` |
-
-### Edit-safety enforcement
-A `PreToolUse` hook (warn mode by default) reminds you if no milens safety check (`impact`/`context`/`overview`/`guard_edit_check`/`edit_check`/`smart_context`) was called before an `Edit`/`Write`/`MultiEdit`. Opt-in strict deny mode is available via `milens hooks guard-set-mode --mode strict`. Both modes consume the check after one edit. See `.milens/hook-state/config.json`. Known caveat: the underlying `PreToolUse` deny mechanism has at least one reliability issue (https://github.com/anthropics/claude-code/issues/4362).
-
-## Overview
-Contains 85 symbols (31 exported) across 16 files.
-
-## Key Symbols
-- **`LangSpec`** [interface] (src/parser/extract.ts:6) — 32 refs
-- **`loadLanguage`** [function] (src/parser/loader.ts:21) — 15 refs
-- **`getParser`** [function] (src/parser/loader.ts:32) — 14 refs
-- **`extractFromTree`** [function] (src/parser/extract.ts:274) — 9 refs
-- **`supportedExtensions`** [function] (src/parser/languages.ts:29) — 6 refs
-- **`extractHtmlScripts`** [function] (src/parser/lang-html.ts:38) — 5 refs
-- **`extractMarkdown`** [function] (src/parser/lang-md.ts:34) — 5 refs
-- **`spec`** [variable] (src/parser/lang-ts.ts:1) — 5 refs
-- **`extractVueScript`** [function] (src/parser/lang-vue.ts:19) — 5 refs
-- **`initTreeSitter`** [function] (src/parser/loader.ts:15) — 5 refs
-- **`clearQueryCache`** [function] (src/parser/extract.ts:79) — 4 refs
-- **`extractHtmlRefs`** [function] (src/parser/lang-html.ts:57) — 4 refs
-- **`extractHtmlLinks`** [function] (src/parser/lang-html.ts:99) — 4 refs
-- **`spec`** [variable] (src/parser/lang-js.ts:1) — 4 refs
-- **`extractVueTemplateRefs`** [function] (src/parser/lang-vue.ts:38) — 4 refs
-
-## Entry Points
-- **`LangSpec`** [interface] — 32 incoming references
-- **`loadLanguage`** [function] — 15 incoming references
-- **`getParser`** [function] — 14 incoming references
-- **`extractFromTree`** [function] — 9 incoming references
-- **`supportedExtensions`** [function] — 6 incoming references
-
-## Dependencies
-- **root**: `CodeSymbol`, `RawImport`, `RawCall`, `RawHeritage`, `RawReExport`, `RawTypeBinding`, `RawAssignmentBinding`, `RawReturnType` (+4 more)
-- **analyzer**: `resolve`
-- **store**: `load`
-
-## Used By
-- **analyzer**: `langForFile`, `supportedExtensions`, `getParser`, `loadLanguage`, `extractFromTree`, `clearQueryCache`, `extractVueScript`, `extractVueTemplateRefs` (+9 more)
-- **server**: `getParser`, `loadLanguage`, `ALL_LANGS`
-- **test**: `getParser`, `loadLanguage`, `extractFromTree`, `extractVueScript`, `extractVueTemplateRefs`, `extractVueCompositionApi`, `extractVueTemplateAst`, `spec` (+11 more)
-
-## Files
-- src/parser/extract.ts
-- src/parser/lang-css.ts
-- src/parser/lang-go.ts
-- src/parser/lang-html.ts
-- src/parser/lang-java.ts
-- src/parser/lang-js.ts
-- src/parser/lang-md.ts
-- src/parser/lang-php.ts
-- src/parser/lang-py.ts
-- src/parser/lang-ruby.ts
-- src/parser/lang-rust.ts
-- src/parser/lang-ts.ts
-- src/parser/lang-vue.ts
-- src/parser/language-provider.ts
-- src/parser/languages.ts
-- src/parser/loader.ts
+---
+generated-by: milens
+name: milens-parser
+description: Code intelligence for the parser area — symbols, dependencies, and entry points
+---
+
+<!-- Generated by milens — safe to delete/regenerate -->
+# Parser
+
+## Working with this area
+When working with code in **parser/**, follow these mandatory safety rules:
+
+### Before editing any symbol in this area:
+1. Call `mcp_milens_impact({target: "<symbol>", repo: "<workspaceRoot>"})` — check blast radius
+2. If depth-1 dependents > 5 → **STOP and warn** before proceeding
+3. Call `mcp_milens_context({name: "<symbol>", repo: "<workspaceRoot>"})` — see all callers/callees
+
+### Before committing changes in this area:
+1. Call `mcp_milens_detect_changes({repo: "<workspaceRoot>"})` — verify scope
+2. If unexpected files changed → **STOP and report**
+
+### Key tools for this area:
+| Task | Tool |
+|---|---|
+| Find all references | `mcp_milens_context` |
+| Check edit safety | `mcp_milens_edit_check` |
+| Text search across files | `mcp_milens_grep` |
+| See file symbols | `mcp_milens_get_file_symbols` |
+
+### Edit-safety enforcement
+A `PreToolUse` hook (warn mode by default) reminds you if no milens safety check (`impact`/`context`/`overview`/`guard_edit_check`/`edit_check`/`smart_context`) was called before an `Edit`/`Write`/`MultiEdit`. Opt-in strict deny mode is available via `milens hooks guard-set-mode --mode strict`. Both modes consume the check after one edit. See `.milens/hook-state/config.json`. Known caveat: the underlying `PreToolUse` deny mechanism has at least one reliability issue (https://github.com/anthropics/claude-code/issues/4362).
+
+## Overview
+Contains 85 symbols (31 exported) across 16 files.
+
+## Key Symbols
+- **`LangSpec`** [interface] (src/parser/extract.ts:6) — 32 refs
+- **`loadLanguage`** [function] (src/parser/loader.ts:21) — 15 refs
+- **`getParser`** [function] (src/parser/loader.ts:32) — 14 refs
+- **`extractFromTree`** [function] (src/parser/extract.ts:274) — 9 refs
+- **`supportedExtensions`** [function] (src/parser/languages.ts:29) — 6 refs
+- **`extractHtmlScripts`** [function] (src/parser/lang-html.ts:38) — 5 refs
+- **`extractMarkdown`** [function] (src/parser/lang-md.ts:34) — 5 refs
+- **`spec`** [variable] (src/parser/lang-ts.ts:1) — 5 refs
+- **`extractVueScript`** [function] (src/parser/lang-vue.ts:19) — 5 refs
+- **`initTreeSitter`** [function] (src/parser/loader.ts:15) — 5 refs
+- **`clearQueryCache`** [function] (src/parser/extract.ts:79) — 4 refs
+- **`extractHtmlRefs`** [function] (src/parser/lang-html.ts:57) — 4 refs
+- **`extractHtmlLinks`** [function] (src/parser/lang-html.ts:99) — 4 refs
+- **`spec`** [variable] (src/parser/lang-js.ts:1) — 4 refs
+- **`extractVueTemplateRefs`** [function] (src/parser/lang-vue.ts:38) — 4 refs
+
+## Entry Points
+- **`LangSpec`** [interface] — 32 incoming references
+- **`loadLanguage`** [function] — 15 incoming references
+- **`getParser`** [function] — 14 incoming references
+- **`extractFromTree`** [function] — 9 incoming references
+- **`supportedExtensions`** [function] — 6 incoming references
+
+## Dependencies
+- **root**: `CodeSymbol`, `RawImport`, `RawCall`, `RawHeritage`, `RawReExport`, `RawTypeBinding`, `RawAssignmentBinding`, `RawReturnType` (+4 more)
+- **analyzer**: `resolve`
+- **store**: `load`
+
+## Used By
+- **analyzer**: `langForFile`, `supportedExtensions`, `getParser`, `loadLanguage`, `extractFromTree`, `clearQueryCache`, `extractVueScript`, `extractVueTemplateRefs` (+9 more)
+- **server**: `getParser`, `loadLanguage`, `ALL_LANGS`
+- **test**: `getParser`, `loadLanguage`, `extractFromTree`, `extractVueScript`, `extractVueTemplateRefs`, `extractVueCompositionApi`, `extractVueTemplateAst`, `spec` (+11 more)
+
+## Files
+- src/parser/extract.ts
+- src/parser/lang-css.ts
+- src/parser/lang-go.ts
+- src/parser/lang-html.ts
+- src/parser/lang-java.ts
+- src/parser/lang-js.ts
+- src/parser/lang-md.ts
+- src/parser/lang-php.ts
+- src/parser/lang-py.ts
+- src/parser/lang-ruby.ts
+- src/parser/lang-rust.ts
+- src/parser/lang-ts.ts
+- src/parser/lang-vue.ts
+- src/parser/language-provider.ts
+- src/parser/languages.ts
+- src/parser/loader.ts

package/.agents/skills/root/SKILL.md

@@ -1,89 +1,89 @@
----
-generated-by: milens
-name: milens-root
-description: Code intelligence for the root area — symbols, dependencies, and entry points
----
-
-<!-- Generated by milens — safe to delete/regenerate -->
-# Root
-
-## Working with this area
-When working with code in **root/**, follow these mandatory safety rules:
-
-### Before editing any symbol in this area:
-1. Call `mcp_milens_impact({target: "<symbol>", repo: "<workspaceRoot>"})` — check blast radius
-2. If depth-1 dependents > 5 → **STOP and warn** before proceeding
-3. Call `mcp_milens_context({name: "<symbol>", repo: "<workspaceRoot>"})` — see all callers/callees
-
-### Before committing changes in this area:
-1. Call `mcp_milens_detect_changes({repo: "<workspaceRoot>"})` — verify scope
-2. If unexpected files changed → **STOP and report**
-
-### Key tools for this area:
-| Task | Tool |
-|---|---|
-| Find all references | `mcp_milens_context` |
-| Check edit safety | `mcp_milens_edit_check` |
-| Text search across files | `mcp_milens_grep` |
-| See file symbols | `mcp_milens_get_file_symbols` |
-
-### Edit-safety enforcement
-A `PreToolUse` hook (warn mode by default) reminds you if no milens safety check (`impact`/`context`/`overview`/`guard_edit_check`/`edit_check`/`smart_context`) was called before an `Edit`/`Write`/`MultiEdit`. Opt-in strict deny mode is available via `milens hooks guard-set-mode --mode strict`. Both modes consume the check after one edit. See `.milens/hook-state/config.json`. Known caveat: the underlying `PreToolUse` deny mechanism has at least one reliability issue (https://github.com/anthropics/claude-code/issues/4362).
-
-## Overview
-Contains 238 symbols (157 exported) across 12 files.
-
-## Key Symbols
-- **`CodeSymbol`** [interface] (src/types.ts:8) — 52 refs
-- **`SymbolLink`** [interface] (src/types.ts:26) — 22 refs
-- **`RawCall`** [interface] (src/types.ts:45) — 18 refs
-- **`isTestFile`** [function] (src/utils.ts:4) — 10 refs
-- **`RawImport`** [interface] (src/types.ts:35) — 9 refs
-- **`RawHeritage`** [interface] (src/types.ts:59) — 7 refs
-- **`ExtractionResult`** [interface] (src/types.ts:67) — 6 refs
-- **`RawTypeBinding`** [interface] (src/types.ts:88) — 6 refs
-- **`RawAssignmentBinding`** [interface] (src/types.ts:96) — 6 refs
-- **`globToRegex`** [function] (src/utils.ts:16) — 6 refs
-- **`RawReturnType`** [interface] (src/types.ts:104) — 5 refs
-- **`RawCallResultBinding`** [interface] (src/types.ts:112) — 5 refs
-- **`AnalysisStats`** [interface] (src/types.ts:135) — 5 refs
-- **`generateAgentsMd`** [function] (src/agents-md.ts:93) — 4 refs
-- **`computeMetrics`** [function] (src/metrics.ts:21) — 4 refs
-
-## Entry Points
-- **`CodeSymbol`** [interface] — 52 incoming references
-- **`SymbolLink`** [interface] — 22 incoming references
-- **`RawCall`** [interface] — 18 incoming references
-- **`isTestFile`** [function] — 10 incoming references
-- **`RawImport`** [interface] — 9 incoming references
-
-## Dependencies
-- **store**: `Database`, `RepoRegistry`, `AnnotationStore`, `runDecayPass`, `getIncomingLinks`, `getAllSymbols`, `getCodebaseSummary`, `findDbPath` (+22 more)
-- **analyzer**: `loadAliases`, `analyze`, `resolve`
-- **ui**: `createProgressReporter`, `finalize`
-- **server**: `startHttp`, `startStdio`, `HookManager`, `defaultOnSessionStart`, `defaultOnSessionEnd`, `defaultOnPreCompact`, `defaultOnPostCompact`, `handleMarkChecked` (+6 more)
-- **security**: `loadRules`, `auditDependencies`
-- **orchestrator**: `Orchestrator`, `subscribe`, `runAndFormat`
-
-## Used By
-- **analyzer**: `isTestFile`, `CodeSymbol`, `ExtractionResult`, `RawImport`, `RawCall`, `RawHeritage`, `RawReExport`, `RawTypeBinding` (+8 more)
-- **orchestrator**: `CodeSymbol`
-- **parser**: `CodeSymbol`, `RawImport`, `RawCall`, `RawHeritage`, `RawReExport`, `RawTypeBinding`, `RawAssignmentBinding`, `RawReturnType` (+4 more)
-- **server**: `generateCrossRefSection`, `globToRegex`
-- **store**: `Annotation`, `AnnotationKey`, `Session`, `EvolutionEvent`, `CodeSymbol`, `SymbolLink`, `RepoEntry`
-- **ui**: `AnalysisStats`
-- **test**: `generateAgentsMd`, `AnnotationKey`, `CodeSymbol`, `SymbolLink`, `computeMetrics`, `formatMetricsReport`, `MilensMetrics`, `RawImport` (+18 more)
-
-## Files
-- AGENTS.md
-- CLAUDE.md
-- CONTRIBUTING.md
-- README.md
-- src/agents-md.ts
-- src/cli.ts
-- src/metrics.ts
-- src/skills.ts
-- src/types.ts
-- src/uninstall.ts
-- src/utils.ts
-- vitest.config.ts
+---
+generated-by: milens
+name: milens-root
+description: Code intelligence for the root area — symbols, dependencies, and entry points
+---
+
+<!-- Generated by milens — safe to delete/regenerate -->
+# Root
+
+## Working with this area
+When working with code in **root/**, follow these mandatory safety rules:
+
+### Before editing any symbol in this area:
+1. Call `mcp_milens_impact({target: "<symbol>", repo: "<workspaceRoot>"})` — check blast radius
+2. If depth-1 dependents > 5 → **STOP and warn** before proceeding
+3. Call `mcp_milens_context({name: "<symbol>", repo: "<workspaceRoot>"})` — see all callers/callees
+
+### Before committing changes in this area:
+1. Call `mcp_milens_detect_changes({repo: "<workspaceRoot>"})` — verify scope
+2. If unexpected files changed → **STOP and report**
+
+### Key tools for this area:
+| Task | Tool |
+|---|---|
+| Find all references | `mcp_milens_context` |
+| Check edit safety | `mcp_milens_edit_check` |
+| Text search across files | `mcp_milens_grep` |
+| See file symbols | `mcp_milens_get_file_symbols` |
+
+### Edit-safety enforcement
+A `PreToolUse` hook (warn mode by default) reminds you if no milens safety check (`impact`/`context`/`overview`/`guard_edit_check`/`edit_check`/`smart_context`) was called before an `Edit`/`Write`/`MultiEdit`. Opt-in strict deny mode is available via `milens hooks guard-set-mode --mode strict`. Both modes consume the check after one edit. See `.milens/hook-state/config.json`. Known caveat: the underlying `PreToolUse` deny mechanism has at least one reliability issue (https://github.com/anthropics/claude-code/issues/4362).
+
+## Overview
+Contains 238 symbols (157 exported) across 12 files.
+
+## Key Symbols
+- **`CodeSymbol`** [interface] (src/types.ts:8) — 52 refs
+- **`SymbolLink`** [interface] (src/types.ts:26) — 22 refs
+- **`RawCall`** [interface] (src/types.ts:45) — 18 refs
+- **`isTestFile`** [function] (src/utils.ts:4) — 10 refs
+- **`RawImport`** [interface] (src/types.ts:35) — 9 refs
+- **`RawHeritage`** [interface] (src/types.ts:59) — 7 refs
+- **`ExtractionResult`** [interface] (src/types.ts:67) — 6 refs
+- **`RawTypeBinding`** [interface] (src/types.ts:88) — 6 refs
+- **`RawAssignmentBinding`** [interface] (src/types.ts:96) — 6 refs
+- **`globToRegex`** [function] (src/utils.ts:16) — 6 refs
+- **`RawReturnType`** [interface] (src/types.ts:104) — 5 refs
+- **`RawCallResultBinding`** [interface] (src/types.ts:112) — 5 refs
+- **`AnalysisStats`** [interface] (src/types.ts:135) — 5 refs
+- **`generateAgentsMd`** [function] (src/agents-md.ts:93) — 4 refs
+- **`computeMetrics`** [function] (src/metrics.ts:21) — 4 refs
+
+## Entry Points
+- **`CodeSymbol`** [interface] — 52 incoming references
+- **`SymbolLink`** [interface] — 22 incoming references
+- **`RawCall`** [interface] — 18 incoming references
+- **`isTestFile`** [function] — 10 incoming references
+- **`RawImport`** [interface] — 9 incoming references
+
+## Dependencies
+- **store**: `Database`, `RepoRegistry`, `AnnotationStore`, `runDecayPass`, `getIncomingLinks`, `getAllSymbols`, `getCodebaseSummary`, `findDbPath` (+22 more)
+- **analyzer**: `loadAliases`, `analyze`, `resolve`
+- **ui**: `createProgressReporter`, `finalize`
+- **server**: `startHttp`, `startStdio`, `HookManager`, `defaultOnSessionStart`, `defaultOnSessionEnd`, `defaultOnPreCompact`, `defaultOnPostCompact`, `handleMarkChecked` (+6 more)
+- **security**: `loadRules`, `auditDependencies`
+- **orchestrator**: `Orchestrator`, `subscribe`, `runAndFormat`
+
+## Used By
+- **analyzer**: `isTestFile`, `CodeSymbol`, `ExtractionResult`, `RawImport`, `RawCall`, `RawHeritage`, `RawReExport`, `RawTypeBinding` (+8 more)
+- **orchestrator**: `CodeSymbol`
+- **parser**: `CodeSymbol`, `RawImport`, `RawCall`, `RawHeritage`, `RawReExport`, `RawTypeBinding`, `RawAssignmentBinding`, `RawReturnType` (+4 more)
+- **server**: `generateCrossRefSection`, `globToRegex`
+- **store**: `Annotation`, `AnnotationKey`, `Session`, `EvolutionEvent`, `CodeSymbol`, `SymbolLink`, `RepoEntry`
+- **ui**: `AnalysisStats`
+- **test**: `generateAgentsMd`, `AnnotationKey`, `CodeSymbol`, `SymbolLink`, `computeMetrics`, `formatMetricsReport`, `MilensMetrics`, `RawImport` (+18 more)
+
+## Files
+- AGENTS.md
+- CLAUDE.md
+- CONTRIBUTING.md
+- README.md
+- src/agents-md.ts
+- src/cli.ts
+- src/metrics.ts
+- src/skills.ts
+- src/types.ts
+- src/uninstall.ts
+- src/utils.ts
+- vitest.config.ts

package/.agents/skills/scripts/SKILL.md

@@ -1,56 +1,56 @@
----
-generated-by: milens
-name: milens-scripts
-description: Code intelligence for the scripts area — symbols, dependencies, and entry points
----
-
-<!-- Generated by milens — safe to delete/regenerate -->
-# Scripts
-
-## Working with this area
-When working with code in **scripts/**, follow these mandatory safety rules:
-
-### Before editing any symbol in this area:
-1. Call `mcp_milens_impact({target: "<symbol>", repo: "<workspaceRoot>"})` — check blast radius
-2. If depth-1 dependents > 5 → **STOP and warn** before proceeding
-3. Call `mcp_milens_context({name: "<symbol>", repo: "<workspaceRoot>"})` — see all callers/callees
-
-### Before committing changes in this area:
-1. Call `mcp_milens_detect_changes({repo: "<workspaceRoot>"})` — verify scope
-2. If unexpected files changed → **STOP and report**
-
-### Key tools for this area:
-| Task | Tool |
-|---|---|
-| Find all references | `mcp_milens_context` |
-| Check edit safety | `mcp_milens_edit_check` |
-| Text search across files | `mcp_milens_grep` |
-| See file symbols | `mcp_milens_get_file_symbols` |
-
-### Edit-safety enforcement
-A `PreToolUse` hook (warn mode by default) reminds you if no milens safety check (`impact`/`context`/`overview`/`guard_edit_check`/`edit_check`/`smart_context`) was called before an `Edit`/`Write`/`MultiEdit`. Opt-in strict deny mode is available via `milens hooks guard-set-mode --mode strict`. Both modes consume the check after one edit. See `.milens/hook-state/config.json`. Known caveat: the underlying `PreToolUse` deny mechanism has at least one reliability issue (https://github.com/anthropics/claude-code/issues/4362).
-
-## Overview
-Contains 80 symbols (0 exported) across 7 files.
-
-## Entry Points
-- **`ghApi`** [function] — 4 incoming references
-- **`exec`** [function] — 3 incoming references
-- **`branch`** [variable] — 3 incoming references
-- **`detectBreakingFromLabels`** [function] — 3 incoming references
-- **`fail`** [function] — 3 incoming references
-
-## Dependencies
-- **analyzer**: `resolve`
-
-## Used By
-- **apps**: `parseArgs`, `generatePrPayload`
-
-## Files
-- scripts/build-standalone.mjs
-- scripts/check-console.mjs
-- scripts/create-pr.cjs
-- scripts/gen-build-info.mjs
-- scripts/pr-generator.cjs
-- scripts/smoke-test.mjs
-- scripts/sync-version.mjs
+---
+generated-by: milens
+name: milens-scripts
+description: Code intelligence for the scripts area — symbols, dependencies, and entry points
+---
+
+<!-- Generated by milens — safe to delete/regenerate -->
+# Scripts
+
+## Working with this area
+When working with code in **scripts/**, follow these mandatory safety rules:
+
+### Before editing any symbol in this area:
+1. Call `mcp_milens_impact({target: "<symbol>", repo: "<workspaceRoot>"})` — check blast radius
+2. If depth-1 dependents > 5 → **STOP and warn** before proceeding
+3. Call `mcp_milens_context({name: "<symbol>", repo: "<workspaceRoot>"})` — see all callers/callees
+
+### Before committing changes in this area:
+1. Call `mcp_milens_detect_changes({repo: "<workspaceRoot>"})` — verify scope
+2. If unexpected files changed → **STOP and report**
+
+### Key tools for this area:
+| Task | Tool |
+|---|---|
+| Find all references | `mcp_milens_context` |
+| Check edit safety | `mcp_milens_edit_check` |
+| Text search across files | `mcp_milens_grep` |
+| See file symbols | `mcp_milens_get_file_symbols` |
+
+### Edit-safety enforcement
+A `PreToolUse` hook (warn mode by default) reminds you if no milens safety check (`impact`/`context`/`overview`/`guard_edit_check`/`edit_check`/`smart_context`) was called before an `Edit`/`Write`/`MultiEdit`. Opt-in strict deny mode is available via `milens hooks guard-set-mode --mode strict`. Both modes consume the check after one edit. See `.milens/hook-state/config.json`. Known caveat: the underlying `PreToolUse` deny mechanism has at least one reliability issue (https://github.com/anthropics/claude-code/issues/4362).
+
+## Overview
+Contains 80 symbols (0 exported) across 7 files.
+
+## Entry Points
+- **`ghApi`** [function] — 4 incoming references
+- **`exec`** [function] — 3 incoming references
+- **`branch`** [variable] — 3 incoming references
+- **`detectBreakingFromLabels`** [function] — 3 incoming references
+- **`fail`** [function] — 3 incoming references
+
+## Dependencies
+- **analyzer**: `resolve`
+
+## Used By
+- **apps**: `parseArgs`, `generatePrPayload`
+
+## Files
+- scripts/build-standalone.mjs
+- scripts/check-console.mjs
+- scripts/create-pr.cjs
+- scripts/gen-build-info.mjs
+- scripts/pr-generator.cjs
+- scripts/smoke-test.mjs
+- scripts/sync-version.mjs

package/.agents/skills/security/SKILL.md

@@ -1,67 +1,67 @@
----
-generated-by: milens
-name: milens-security
-description: Code intelligence for the security area — symbols, dependencies, and entry points
----
-
-<!-- Generated by milens — safe to delete/regenerate -->
-# Security
-
-## Working with this area
-When working with code in **security/**, follow these mandatory safety rules:
-
-### Before editing any symbol in this area:
-1. Call `mcp_milens_impact({target: "<symbol>", repo: "<workspaceRoot>"})` — check blast radius
-2. If depth-1 dependents > 5 → **STOP and warn** before proceeding
-3. Call `mcp_milens_context({name: "<symbol>", repo: "<workspaceRoot>"})` — see all callers/callees
-
-### Before committing changes in this area:
-1. Call `mcp_milens_detect_changes({repo: "<workspaceRoot>"})` — verify scope
-2. If unexpected files changed → **STOP and report**
-
-### Key tools for this area:
-| Task | Tool |
-|---|---|
-| Find all references | `mcp_milens_context` |
-| Check edit safety | `mcp_milens_edit_check` |
-| Text search across files | `mcp_milens_grep` |
-| See file symbols | `mcp_milens_get_file_symbols` |
-
-### Edit-safety enforcement
-A `PreToolUse` hook (warn mode by default) reminds you if no milens safety check (`impact`/`context`/`overview`/`guard_edit_check`/`edit_check`/`smart_context`) was called before an `Edit`/`Write`/`MultiEdit`. Opt-in strict deny mode is available via `milens hooks guard-set-mode --mode strict`. Both modes consume the check after one edit. See `.milens/hook-state/config.json`. Known caveat: the underlying `PreToolUse` deny mechanism has at least one reliability issue (https://github.com/anthropics/claude-code/issues/4362).
-
-## Overview
-Contains 47 symbols (17 exported) across 2 files.
-
-## Key Symbols
-- **`loadRules`** [function] (src/security/rules.ts:1301) — 6 refs
-- **`auditDependencies`** [function] (src/security/deps.ts:732) — 4 refs
-- **`detectEcosystem`** [function] (src/security/deps.ts:512) — 3 refs
-- **`parseDependencies`** [function] (src/security/deps.ts:524) — 3 refs
-- **`checkVulnerabilities`** [function] (src/security/deps.ts:687) — 3 refs
-- **`Ecosystem`** [type] (src/security/deps.ts:8) — 3 refs
-- **`ALL_RULES`** [variable] (src/security/rules.ts:99) — 3 refs
-- **`VulnerabilityReport`** [interface] (src/security/deps.ts:26) — 2 refs
-- **`getRulesByCategory`** [function] (src/security/rules.ts:1308) — 2 refs
-- **`getRulesBySeverity`** [function] (src/security/rules.ts:1312) — 2 refs
-- **`SecurityCategory`** [type] (src/security/rules.ts:3) — 1 refs
-- **`Dependency`** [interface] (src/security/deps.ts:10) — 0 refs
-- **`Vulnerability`** [interface] (src/security/deps.ts:16) — 0 refs
-- **`SecurityRule`** [interface] (src/security/rules.ts:31) — 0 refs
-- **`SecurityMatch`** [interface] (src/security/rules.ts:47) — 0 refs
-
-## Entry Points
-- **`readManifest`** [function] — 6 incoming references
-- **`loadRules`** [function] — 6 incoming references
-- **`auditDependencies`** [function] — 4 incoming references
-- **`detectEcosystem`** [function] — 3 incoming references
-- **`parseDependencies`** [function] — 3 incoming references
-
-## Used By
-- **root**: `loadRules`, `auditDependencies`
-- **server**: `loadRules`
-- **test**: `detectEcosystem`, `parseDependencies`, `checkVulnerabilities`, `auditDependencies`, `loadRules`, `getRulesByCategory`, `getRulesBySeverity`
-
-## Files
-- src/security/deps.ts
-- src/security/rules.ts
+---
+generated-by: milens
+name: milens-security
+description: Code intelligence for the security area — symbols, dependencies, and entry points
+---
+
+<!-- Generated by milens — safe to delete/regenerate -->
+# Security
+
+## Working with this area
+When working with code in **security/**, follow these mandatory safety rules:
+
+### Before editing any symbol in this area:
+1. Call `mcp_milens_impact({target: "<symbol>", repo: "<workspaceRoot>"})` — check blast radius
+2. If depth-1 dependents > 5 → **STOP and warn** before proceeding
+3. Call `mcp_milens_context({name: "<symbol>", repo: "<workspaceRoot>"})` — see all callers/callees
+
+### Before committing changes in this area:
+1. Call `mcp_milens_detect_changes({repo: "<workspaceRoot>"})` — verify scope
+2. If unexpected files changed → **STOP and report**
+
+### Key tools for this area:
+| Task | Tool |
+|---|---|
+| Find all references | `mcp_milens_context` |
+| Check edit safety | `mcp_milens_edit_check` |
+| Text search across files | `mcp_milens_grep` |
+| See file symbols | `mcp_milens_get_file_symbols` |
+
+### Edit-safety enforcement
+A `PreToolUse` hook (warn mode by default) reminds you if no milens safety check (`impact`/`context`/`overview`/`guard_edit_check`/`edit_check`/`smart_context`) was called before an `Edit`/`Write`/`MultiEdit`. Opt-in strict deny mode is available via `milens hooks guard-set-mode --mode strict`. Both modes consume the check after one edit. See `.milens/hook-state/config.json`. Known caveat: the underlying `PreToolUse` deny mechanism has at least one reliability issue (https://github.com/anthropics/claude-code/issues/4362).
+
+## Overview
+Contains 47 symbols (17 exported) across 2 files.
+
+## Key Symbols
+- **`loadRules`** [function] (src/security/rules.ts:1301) — 6 refs
+- **`auditDependencies`** [function] (src/security/deps.ts:732) — 4 refs
+- **`detectEcosystem`** [function] (src/security/deps.ts:512) — 3 refs
+- **`parseDependencies`** [function] (src/security/deps.ts:524) — 3 refs
+- **`checkVulnerabilities`** [function] (src/security/deps.ts:687) — 3 refs
+- **`Ecosystem`** [type] (src/security/deps.ts:8) — 3 refs
+- **`ALL_RULES`** [variable] (src/security/rules.ts:99) — 3 refs
+- **`VulnerabilityReport`** [interface] (src/security/deps.ts:26) — 2 refs
+- **`getRulesByCategory`** [function] (src/security/rules.ts:1308) — 2 refs
+- **`getRulesBySeverity`** [function] (src/security/rules.ts:1312) — 2 refs
+- **`SecurityCategory`** [type] (src/security/rules.ts:3) — 1 refs
+- **`Dependency`** [interface] (src/security/deps.ts:10) — 0 refs
+- **`Vulnerability`** [interface] (src/security/deps.ts:16) — 0 refs
+- **`SecurityRule`** [interface] (src/security/rules.ts:31) — 0 refs
+- **`SecurityMatch`** [interface] (src/security/rules.ts:47) — 0 refs
+
+## Entry Points
+- **`readManifest`** [function] — 6 incoming references
+- **`loadRules`** [function] — 6 incoming references
+- **`auditDependencies`** [function] — 4 incoming references
+- **`detectEcosystem`** [function] — 3 incoming references
+- **`parseDependencies`** [function] — 3 incoming references
+
+## Used By
+- **root**: `loadRules`, `auditDependencies`
+- **server**: `loadRules`
+- **test**: `detectEcosystem`, `parseDependencies`, `checkVulnerabilities`, `auditDependencies`, `loadRules`, `getRulesByCategory`, `getRulesBySeverity`
+
+## Files
+- src/security/deps.ts
+- src/security/rules.ts