@levnikolaevich/hex-line-mcp 1.9.0 → 1.11.0

package/README.md

@@ -11,7 +11,7 @@ Every line carries an FNV-1a content hash. Every edit must present those hashes
 
 ## Features
 
-### 10 MCP Tools
+### 9 MCP Tools
 
 Core day-to-day tools:
 
@@ -25,20 +25,18 @@ Core day-to-day tools:
 Advanced / occasional:
 
 - `write_file`
-- `directory_tree`
-- `get_file_info`
+- `inspect_path`
 - `changes`
 
 | Tool | Description | Key Feature |
 |------|-------------|-------------|
-| `read_file` | Read file with hash-annotated lines, checksums, and revision | Partial reads via `offset`/`limit` or `ranges`, compact output by default |
+| `read_file` | Read file with hash-annotated lines, checksums, revision, and automatic graph hints when available | Partial reads via `offset`/`limit` or `ranges`, compact output by default |
 | `edit_file` | Revision-aware anchor edits (`set_line`, `replace_lines`, `insert_after`, `replace_between`) | Batched same-file edits + conservative auto-rebase |
 | `write_file` | Create new file or overwrite, auto-creates parent dirs | Path validation, no hash overhead |
 | `grep_search` | Search with ripgrep, 3 output modes, per-group checksums | Plain `files`/`count`, compact edit-ready `content` |
-| `outline` | AST-based structural overview with hash anchors via tree-sitter WASM. Supports code (15+ langs) and fence-aware markdown headings | 95% token reduction, direct edit anchors |
+| `outline` | AST-based structural overview with hash anchors via tree-sitter WASM. Supports JavaScript/TypeScript, Python, C#, PHP, and fence-aware markdown headings | 95% token reduction, direct edit anchors |
 | `verify` | Check if held checksums / revision are still current | Staleness check without full re-read |
-| `directory_tree` | Compact directory tree with root .gitignore support | Skips node_modules/.git, shows file sizes |
-| `get_file_info` | File metadata without reading content | Size, lines, mtime, type, binary detection |
+| `inspect_path` | Unified file-or-directory inspection | File metadata for files, tree or pattern search for directories |
 | `changes` | Compare file against git ref, shows added/removed/modified symbols | AST-level semantic diff |
 | `bulk_replace` | Search-and-replace across multiple files by glob | Compact summary (default) or capped diffs via `format`, dry_run, max_files |
 
@@ -93,17 +91,20 @@ Comparative built-in vs hex-line benchmarks are maintained outside this package.
 
 ### Optional Graph Enrichment
 
-If a project already has `.hex-skills/codegraph/index.db`, `hex-line` can add lightweight graph hints to `read_file`, `outline`, `grep_search`, and `edit_file`.
+If a project already has `.hex-skills/codegraph/index.db`, `hex-line` automatically adds lightweight graph hints to `read_file`, `outline`, `grep_search`, `edit_file`, and `changes`.
 
-- Graph enrichment is optional. If `.hex-skills/codegraph/index.db` is missing, `hex-line` falls back to standard behavior silently.
+- Graph enrichment is optional. If `.hex-skills/codegraph/index.db` is missing, stale, or unreadable, `hex-line` falls back to standard behavior silently.
 - `better-sqlite3` is optional. If it is unavailable, `hex-line` still works without graph hints.
-- `edit_file` reports **Call impact**, not full semantic blast radius. The warning uses call-graph callers only.
+- `read_file`, `outline`, and `grep_search` stay compact: they only surface high-signal local facts such as `api`, framework entrypoints, callers, flow, and clone hints.
+- `edit_file` and `changes` surface the deeper review layer: external callers, downstream return/property flow, clone peers, public API risk, framework entrypoint risk, and same-name sibling warnings when present.
 
 `hex-line` does not read `hex-graph` internals directly anymore. The integration uses a small read-only contract exposed by `hex-graph-mcp`:
 
-- `hex_line_contract`
-- `hex_line_symbol_annotations`
-- `hex_line_call_edges`
+- `hex_line_symbols`
+- `hex_line_line_facts`
+- `hex_line_edit_impacts`
+- `hex_line_edit_impact_facts`
+- `hex_line_clone_siblings`
 
 ## Tools Reference
 
@@ -131,16 +132,15 @@ Use `bulk_replace` for text rename patterns across one or more files. Returns co
 
 ### read_file
 
-Read a file as canonical edit-ready blocks. Each valid range becomes a `read_range` block with absolute span, line entries, and a checksum covering exactly the emitted lines. Invalid ranges become explicit diagnostic blocks. Supports batch reads, multi-range reads, and directory listing.
+Read a file as canonical edit-ready blocks. Each valid range becomes a `read_range` block with absolute span, line entries, and a checksum covering exactly the emitted lines. Invalid ranges become explicit diagnostic blocks. Supports batch reads and multi-range reads. Directories go through `inspect_path`.
 
 | Parameter | Type | Required | Description |
 |-----------|------|----------|-------------|
-| `path` | string | yes | File or directory path |
+| `path` | string | yes | File path |
 | `paths` | string[] | no | Array of file paths to read (batch mode) |
 | `offset` | number | no | Start line, 1-indexed (default: 1) |
 | `limit` | number | no | Max lines to return (default: 2000, 0 = all) |
 | `ranges` | array | no | Explicit line ranges, e.g. `[{ "start": 10, "end": 30 }]` |
-| `include_graph` | boolean | no | Opt in to graph annotations when the graph index exists |
 | `plain` | boolean | no | Omit hashes, output `lineNum\|content` instead |
 
 Default output is compact but block-structured:
@@ -227,13 +227,13 @@ Search file contents using ripgrep. Three output modes: `content` (canonical `se
 
 ### outline
 
-AST-based structural outline with hash anchors for direct `edit_file` usage. Supports code files (15+ languages) and fence-aware markdown heading navigation (`.md`/`.mdx`). Each entry includes a hash tag for immediate anchor use without intermediate `read_file`.
+AST-based structural outline with hash anchors for direct `edit_file` usage. Supports JavaScript/TypeScript, Python, C#, PHP, and fence-aware markdown heading navigation (`.md`/`.mdx`). Each entry includes a hash tag for immediate anchor use without intermediate `read_file`.
 
 | Parameter | Type | Required | Description |
 |-----------|------|----------|-------------|
 | `path` | string | yes | Source file path |
 
-Supported languages: JavaScript, TypeScript (JSX/TSX), Python, Go, Rust, Java, C, C++, C#, Ruby, PHP, Kotlin, Swift, Bash -- 15+ via tree-sitter WASM.
+Supported languages: JavaScript (`.js`, `.mjs`, `.cjs`, `.jsx`), TypeScript (`.ts`, `.tsx`), Python (`.py`), C# (`.cs`), and PHP (`.php`) via tree-sitter WASM.
 
 Not for `.json`, `.yaml`, `.txt` -- use `read_file` directly for those.
 
@@ -260,30 +260,22 @@ changed_ranges: 10-12(replace)
 STALE 10-12 checksum: 10-12:oldc0de0 current=10-12:newc0de0
 ```
 
-### directory_tree
+### inspect_path
 
-Compact directory tree with root .gitignore support (path-based rules, negation, dir-only). Nested .gitignore files are not loaded.
+Inspect a file or directory path without guessing which low-level tool to call first.
 
 | Parameter | Type | Required | Description |
 |-----------|------|----------|-------------|
-| `path` | string | yes | Directory path |
+| `path` | string | yes | File or directory path |
 | `pattern` | string | no | Glob filter on names (e.g. `"*-mcp"`, `"*.mjs"`). Returns flat match list instead of tree |
 | `type` | string | no | `"file"`, `"dir"`, or `"all"` (default). Like `find -type f/d` |
 | `max_depth` | number | no | Max recursion depth (default: 3, or 20 in pattern mode) |
 | `gitignore` | boolean | no | Respect root .gitignore patterns (default: true). Nested .gitignore not supported |
-| `format` | string | no | `"compact"` = names only, no sizes, depth 1. `"full"` = default with sizes |
-
-Skips `node_modules`, `.git`, `dist`, `build`, `__pycache__`, `.next`, `coverage` by default.
-
-### get_file_info
-
-File metadata without reading content.
-
-| Parameter | Type | Required | Description |
-|-----------|------|----------|-------------|
-| `path` | string | yes | File path |
+| `format` | string | no | `"compact"` = shorter path view. `"full"` = include sizes / metadata where available |
 
-Returns: size, line count, modification time (absolute + relative), file type, binary detection.
+- For regular files it returns compact metadata: size, line count when cheap, modification time, type, and binary flag.
+- For directories it returns a gitignore-aware tree.
+- With `pattern`, it switches to flat match mode and works as the preferred replacement for `find` / recursive `ls`.
 
 ## Hook
 
@@ -322,11 +314,10 @@ Injects a short operational workflow into agent context at session start: no `To
 
 ```
 hex-line-mcp/
-  server.mjs          MCP server (stdio transport, 11 tools)
+  server.mjs          MCP server (stdio transport, 9 tools)
   hook.mjs            Unified hook (PreToolUse + PostToolUse + SessionStart)
   package.json
   lib/
-    hash.mjs          FNV-1a hashing, 2-char tags, range checksums
     read.mjs          File reading with hash annotation
     edit.mjs          Anchor-based edits, diff output
     search.mjs        ripgrep wrapper with hash-annotated results
@@ -334,13 +325,15 @@ hex-line-mcp/
     verify.mjs        Range checksum verification
     info.mjs          File metadata (size, lines, mtime, type)
     tree.mjs          Directory tree with .gitignore support
+    inspect-path.mjs  Unified file/directory inspection
     changes.mjs       Semantic git diff via AST
     bulk-replace.mjs  Multi-file search-and-replace
     setup.mjs         Claude hook installation + output style setup
     format.mjs        Output formatting utilities
-    coerce.mjs        Parameter pass-through (identity)
     security.mjs      Path validation, binary detection, size limits
-    normalize.mjs     Output normalization, deduplication, truncation
+    @levnikolaevich/hex-common/
+      text-protocol/hash.mjs   Shared FNV-1a hashing and checksum protocol
+      output/normalize.mjs     Shared output normalization helpers
 ```
 
 ### Hash Format
@@ -390,7 +383,7 @@ The edit is rejected with an error showing which lines changed since the last re
 <details>
 <summary><b>Is outline available for all file types?</b></summary>
 
-Outline works on code files (15+ languages via tree-sitter WASM) and markdown heading navigation (`.md`/`.mdx`, fenced code blocks ignored). For JSON, YAML, and text files use `read_file` directly. Each outline entry includes a hash anchor (`tag.line-range: symbol`) for direct use in `edit_file`.
+Outline works on JavaScript/TypeScript, Python, C#, PHP, and markdown heading navigation (`.md`/`.mdx`, fenced code blocks ignored). For JSON, YAML, and text files use `read_file` directly. Each outline entry includes a hash anchor (`tag.line-range: symbol`) for direct use in `edit_file`.
 
 </details>
 

package/dist/artifacts/tree-sitter/manifest.json

@@ -0,0 +1,57 @@
+{
+  "generated_from": {
+    "source": "tree-sitter-cli-build",
+    "tree_sitter_cli_version": "0.26.8",
+    "note": "Repo-owned grammar WASM artifacts built from pinned npm grammar packages with the current tree-sitter CLI."
+  },
+  "grammars": [
+    {
+      "grammar": "javascript",
+      "file": "tree-sitter-javascript.wasm",
+      "package": "tree-sitter-javascript",
+      "version": "0.25.0",
+      "source_subdir": null,
+      "sha256": "29d37c59b7797fa1c56419816d1730d5ff5e2ed2077bc44c5d6f50082be09136"
+    },
+    {
+      "grammar": "typescript",
+      "file": "tree-sitter-typescript.wasm",
+      "package": "tree-sitter-typescript",
+      "version": "0.23.2",
+      "source_subdir": "typescript",
+      "sha256": "f7c442260d8bf63b89762af2663655d153f84d169b4b8fedd15a5ba9b29ed3a4"
+    },
+    {
+      "grammar": "tsx",
+      "file": "tree-sitter-tsx.wasm",
+      "package": "tree-sitter-typescript",
+      "version": "0.23.2",
+      "source_subdir": "tsx",
+      "sha256": "4f795eb1fd00d14b7d284add59df8796d3c4b30e49d27979cba70c02298d5f67"
+    },
+    {
+      "grammar": "python",
+      "file": "tree-sitter-python.wasm",
+      "package": "tree-sitter-python",
+      "version": "0.25.0",
+      "source_subdir": null,
+      "sha256": "6183aa51eecace847badb487766e33a0f7725c257b479a0b89c9ff1bcec9c610"
+    },
+    {
+      "grammar": "c_sharp",
+      "file": "tree-sitter-c_sharp.wasm",
+      "package": "tree-sitter-c-sharp",
+      "version": "0.23.1",
+      "source_subdir": null,
+      "sha256": "974cb3e3302c04a5b5e6734494af2ed2fd0c284c38693316ef013922639aecf2"
+    },
+    {
+      "grammar": "php",
+      "file": "tree-sitter-php.wasm",
+      "package": "tree-sitter-php",
+      "version": "0.24.2",
+      "source_subdir": "php",
+      "sha256": "393e65be27e256ed2f1a43e0e70e43de05f77b5563d7dd877bdb44760d5560a6"
+    }
+  ]
+}

package/dist/hook.mjs

@@ -54,7 +54,7 @@ function normalizeOutput(text, opts = {}) {
 }
 
 // hook.mjs
-import { readFileSync, statSync } from "node:fs";
+import { readFileSync, statSync, writeSync } from "node:fs";
 import { resolve } from "node:path";
 import { homedir } from "node:os";
 import { fileURLToPath } from "node:url";
@@ -97,27 +97,15 @@ var OUTLINEABLE_EXT = /* @__PURE__ */ new Set([
   ".ts",
   ".tsx",
   ".py",
-  ".go",
-  ".rs",
-  ".java",
-  ".c",
-  ".h",
-  ".cpp",
   ".cs",
-  ".rb",
-  ".php",
-  ".kt",
-  ".swift",
-  ".sh",
-  ".bash"
+  ".php"
 ]);
 var REVERSE_TOOL_HINTS = {
   "mcp__hex-line__read_file": "Read (file_path, offset, limit)",
   "mcp__hex-line__edit_file": "Edit (old_string, new_string, replace_all)",
   "mcp__hex-line__write_file": "Write (file_path, content)",
   "mcp__hex-line__grep_search": "Grep (pattern, path)",
-  "mcp__hex-line__directory_tree": "Glob (pattern) or Bash(ls)",
-  "mcp__hex-line__get_file_info": "Bash(stat/wc)",
+  "mcp__hex-line__inspect_path": "Path info / tree / Bash(ls,stat)",
   "mcp__hex-line__outline": "Read with offset/limit",
   "mcp__hex-line__verify": "Read (re-read file to check freshness)",
   "mcp__hex-line__changes": "Bash(git diff)",
@@ -131,8 +119,8 @@ var TOOL_HINTS = {
   cat: "mcp__hex-line__read_file (not cat/head/tail/less/more)",
   head: "mcp__hex-line__read_file with limit param (not head)",
   tail: "mcp__hex-line__read_file with offset param (not tail)",
-  ls: "mcp__hex-line__directory_tree with pattern param (not ls/find/tree). E.g. pattern='*-mcp' type='dir'",
-  stat: "mcp__hex-line__get_file_info (not stat/wc/file)",
+  ls: "mcp__hex-line__inspect_path for tree or pattern search (not ls/find/tree). E.g. pattern='*-mcp' type='dir'",
+  stat: "mcp__hex-line__inspect_path for compact file metadata (not stat/wc/file)",
   grep: "mcp__hex-line__grep_search (not grep/rg). Params: output, literal, context_before, context_after, multiline",
   sed: "mcp__hex-line__edit_file for hash edits, or mcp__hex-line__bulk_replace for text rename (not sed -i)",
   diff: "mcp__hex-line__changes (not diff). Git diff with change symbols",
@@ -141,6 +129,7 @@ var TOOL_HINTS = {
   changes: "mcp__hex-line__changes (git diff with change symbols)",
   bulk: "mcp__hex-line__bulk_replace (multi-file search-replace)"
 };
+var DEFERRED_HINT = "If schemas not loaded: ToolSearch('+hex-line read edit')";
 var BASH_REDIRECTS = [
   { regex: /^cat\s+\S+/, key: "cat" },
   { regex: /^head\s+/, key: "head" },
@@ -282,16 +271,25 @@ function getHookMode() {
   }
   return _hookMode;
 }
+function safeExit(fd, data, code) {
+  writeSync(fd, data);
+  process.exit(code);
+}
+function debugLog(action, reason) {
+  writeSync(2, `[hex-hook] ${action}: ${reason}
+`);
+}
 function block(reason, context) {
+  const msg = context ? `${reason}
+${context}` : reason;
   const output = {
     hookSpecificOutput: {
       permissionDecision: "deny"
     },
-    systemMessage: context ? `${reason}
-${context}` : reason
+    systemMessage: msg
   };
-  process.stdout.write(JSON.stringify(output));
-  process.exit(2);
+  debugLog("BLOCK", reason);
+  safeExit(1, JSON.stringify(output), 2);
 }
 function advise(reason, context) {
   const output = {
@@ -301,8 +299,7 @@ function advise(reason, context) {
     systemMessage: context ? `${reason}
 ${context}` : reason
   };
-  process.stdout.write(JSON.stringify(output));
-  process.exit(0);
+  safeExit(1, JSON.stringify(output), 0);
 }
 function redirect(reason, context) {
   if (getHookMode() === "advisory") {
@@ -324,24 +321,20 @@ function handlePreToolUse(data) {
     if (BINARY_EXT.has(extOf(filePath))) {
       process.exit(0);
     }
-    const normalPath = filePath.replace(/\\/g, "/");
-    if (normalPath.includes(".claude/plans/") || normalPath.includes("AppData")) {
+    const resolvedNorm = resolveToolPath(filePath).replace(/\\/g, "/");
+    const cwdNorm = process.cwd().replace(/\\/g, "/");
+    const homeNorm = homedir().replace(/\\/g, "/");
+    const claudeAllow = [
+      cwdNorm + "/.claude/settings.json",
+      cwdNorm + "/.claude/settings.local.json",
+      homeNorm + "/.claude/settings.json",
+      homeNorm + "/.claude/settings.local.json"
+    ];
+    if (claudeAllow.some((p) => resolvedNorm.toLowerCase() === p.toLowerCase())) {
       process.exit(0);
     }
-    const ALLOWED_CONFIGS = /* @__PURE__ */ new Set(["settings.json", "settings.local.json"]);
-    const fileName = normalPath.split("/").pop();
-    if (ALLOWED_CONFIGS.has(fileName)) {
-      let candidate = filePath;
-      if (candidate.startsWith("~/")) {
-        candidate = homedir().replace(/\\/g, "/") + candidate.slice(1);
-      }
-      const absPath = resolve(process.cwd(), candidate).replace(/\\/g, "/");
-      const projectClaude = resolve(process.cwd(), ".claude").replace(/\\/g, "/") + "/";
-      const globalClaude = resolve(homedir(), ".claude").replace(/\\/g, "/") + "/";
-      const cmp = process.platform === "win32" ? (a, b) => a.toLowerCase().startsWith(b.toLowerCase()) : (a, b) => a.startsWith(b);
-      if (cmp(absPath, projectClaude) || cmp(absPath, globalClaude)) {
-        process.exit(0);
-      }
+    if (resolvedNorm.includes("/.claude/")) {
+      redirect("Protected .claude/ path. Use built-in tools for .claude/ config files.");
     }
     if (toolName === "Read") {
       if (isPartialRead(toolInput)) {
@@ -349,29 +342,30 @@ function handlePreToolUse(data) {
       }
       if (fileSize !== null && fileSize <= LARGE_FILE_BYTES) {
         const ext2 = filePath ? extOf(filePath) : "";
-        const hint = filePath && OUTLINEABLE_EXT.has(ext2) ? `mcp__hex-line__outline(path="${filePath}") gives a compact structural map. For edits, use mcp__hex-line__read_file(path="${filePath}") with ranges.` : filePath ? `NEXT READ: use mcp__hex-line__read_file(path="${filePath}"). Built-in Read allowed this time but wastes edit context.` : "NEXT READ: use mcp__hex-line__read_file. Built-in Read allowed this time but wastes edit context.";
-        advise(hint);
+        const hint = filePath && OUTLINEABLE_EXT.has(ext2) ? `Use mcp__hex-line__outline(path="${filePath}") for structure, then mcp__hex-line__read_file(path="${filePath}") with ranges.` : filePath ? `Use mcp__hex-line__read_file(path="${filePath}"). Built-in Read wastes edit context.` : "Use mcp__hex-line__read_file. Built-in Read wastes edit context.";
+        advise(hint, DEFERRED_HINT);
       }
       const ext = filePath ? extOf(filePath) : "";
-      const outlineHint = filePath && OUTLINEABLE_EXT.has(ext) ? `Use mcp__hex-line__outline(path="${filePath}") for structure, then mcp__hex-line__read_file(path="${filePath}") with ranges to read only what you need.` : filePath ? `Use mcp__hex-line__read_file(path="${filePath}") with ranges or offset/limit` : "Use mcp__hex-line__directory_tree or mcp__hex-line__read_file";
-      redirect(outlineHint, "Do not use built-in Read for full reads of large files.");
+      const outlineHint = filePath && OUTLINEABLE_EXT.has(ext) ? `Use mcp__hex-line__outline(path="${filePath}") for structure, then mcp__hex-line__read_file(path="${filePath}") with ranges to read only what you need.` : filePath ? `Use mcp__hex-line__read_file(path="${filePath}") with ranges or offset/limit` : "Use mcp__hex-line__inspect_path or mcp__hex-line__read_file";
+      redirect(outlineHint, "Do not use built-in Read for full reads of large files.\n" + DEFERRED_HINT);
     }
     if (toolName === "Edit") {
       const oldText = String(toolInput.old_string || "");
       const isLargeEdit = Boolean(toolInput.replace_all) || oldText.length > LARGE_EDIT_CHARS || fileSize !== null && fileSize > LARGE_FILE_BYTES;
       if (!isLargeEdit) {
-        process.exit(0);
+        const editHint = filePath ? `Prefer mcp__hex-line__edit_file(path="${filePath}") for hash-verified edits.` : "Prefer mcp__hex-line__edit_file for hash-verified edits.";
+        advise(editHint);
       }
       const target = filePath ? `Use mcp__hex-line__grep_search or mcp__hex-line__read_file, then mcp__hex-line__edit_file with path="${filePath}"` : "Use mcp__hex-line__grep_search or mcp__hex-line__read_file, then mcp__hex-line__edit_file";
-      redirect(target, "For large or repeated edits: locate anchors/checksums first, then call edit_file once with batched edits.");
+      redirect(target, "For large or repeated edits: locate anchors/checksums first, then call edit_file once with batched edits.\n" + DEFERRED_HINT);
     }
     if (toolName === "Write") {
       const pathNote = filePath ? ` with path="${filePath}"` : "";
-      redirect(`Use mcp__hex-line__write_file${pathNote}`, TOOL_HINTS.Write);
+      redirect(`Use mcp__hex-line__write_file${pathNote}`, TOOL_HINTS.Write + "\n" + DEFERRED_HINT);
     }
     if (toolName === "Grep") {
       const pathNote = filePath ? ` with path="${filePath}"` : "";
-      redirect(`Use mcp__hex-line__grep_search${pathNote}`, TOOL_HINTS.Grep);
+      redirect(`Use mcp__hex-line__grep_search${pathNote}`, TOOL_HINTS.Grep + "\n" + DEFERRED_HINT);
     }
   }
   if (toolName === "Bash") {
@@ -457,8 +451,7 @@ function handlePostToolUse(data) {
     `Original: ${originalCount} lines | Filtered: ${filteredCount} lines`,
     "=".repeat(50)
   ].join("\n");
-  process.stderr.write(output);
-  process.exit(2);
+  safeExit(2, output, 2);
 }
 function handleSessionStart() {
   const settingsFiles = [
@@ -479,9 +472,8 @@ function handleSessionStart() {
     }
   }
   const prefix = styleActive ? "Hex-line MCP available. Output style active.\n" : "Hex-line MCP available.\n";
-  const msg = prefix + "Call hex-line tools directly. Do not use ToolSearch for hex-line tools.\nWorkflow:\n- Discovery: outline for code and markdown files, read_file for targeted reads, grep_search for symbol/text lookup\n- Read cheaply: prefer offset/limit or ranges; avoid full-file Read on large files\n- Edit safely: read/grep first, then one batched edit_file call per file with base_revision when available\n- Verify before reread: use verify to check checksums or revision freshness\n- Multi-file rename/refactor: use bulk_replace\n- New files: use write_file\nExceptions: images, PDFs, notebooks, .claude/settings.json, .claude/settings.local.json use built-in Read. Glob is always OK.";
-  process.stdout.write(JSON.stringify({ systemMessage: msg }));
-  process.exit(0);
+  const msg = prefix + "<hex-line_instructions>\n  <deferred_loading>If hex-line schemas not loaded, run: ToolSearch('+hex-line read edit')</deferred_loading>\n  <exploration>\n    <rule>Use outline for structure (code + markdown), not Read. ~10-20 lines vs hundreds.</rule>\n    <rule>Use read_file with offset/limit or ranges for targeted reads.</rule>\n    <rule>Use grep_search before editing to get hash anchors.</rule>\n  </exploration>\n  <editing>\n    <path name='surgical'>grep_search \u2192 edit_file (fastest: hash-verified, no full read needed)</path>\n    <path name='exploratory'>outline \u2192 read_file (ranges) \u2192 edit_file with base_revision</path>\n    <path name='multi-file'>bulk_replace for text rename/refactor across files</path>\n  </editing>\n  <tips>\n    <tip>Carry revision from read_file into base_revision on edit_file.</tip>\n    <tip>If edit returns CONFLICT, call verify \u2014 only reread when STALE.</tip>\n    <tip>Batch multiple edits to same file in one edit_file call.</tip>\n    <tip>Use write_file for new files (no prior Read needed).</tip>\n  </tips>\n  <exceptions>Built-in Read OK for: images, PDFs, notebooks, Glob (always), .claude/settings.json</exceptions>\n</hex-line_instructions>";
+  safeExit(1, JSON.stringify({ systemMessage: msg }), 0);
 }
 var _norm = (p) => p.replace(/\\/g, "/");
 if (_norm(process.argv[1]) === _norm(fileURLToPath(import.meta.url))) {