feat: add Codebase Intelligence — repo map with PageRank-ranked structural summaries

README.md

@@ -154,6 +154,7 @@ Advanced and source-build guides:
 - **Images**: URL and base64 image inputs for providers that support vision
 - **Provider profiles**: Guided setup plus saved `.openclaude-profile.json` support
 - **Local and remote model backends**: Cloud APIs, local servers, and Apple Silicon local inference
+- **Codebase intelligence (repo map)**: Structural map of the repository ranked by PageRank importance, auto-injected into context when the `REPO_MAP` flag is enabled. Inspect with `/repomap`. See [docs/repo-map.md](docs/repo-map.md) for details.
 
 ## Provider Notes
 

docs/repo-map.md

@@ -0,0 +1,67 @@
+# Codebase Intelligence — Repo Map
+
+The repo map feature gives the AI model structural awareness of your codebase at the start of each session. Instead of the model needing to explore the repository with `Grep`, `Glob`, and `Read` calls, it starts with a ranked summary of the most important files and their key signatures.
+
+## How it works
+
+1. **File enumeration** — Lists all tracked files via `git ls-files` (falls back to a manual directory walk when not in a git repo)
+2. **Symbol extraction** — Parses each supported source file with tree-sitter to extract function, class, type, and interface definitions, plus cross-file references
+3. **Reference graph** — Builds a directed graph where an edge from file A to file B means A references a symbol defined in B. Edges are weighted by reference count multiplied by the IDF (inverse document frequency) of the symbol name — common names like `get`, `set`, `value` contribute less
+4. **PageRank** — Ranks files by structural importance using PageRank. Files imported by many others rank highest
+5. **Rendering** — Walks ranked files top-down, emitting file paths and definition signatures, stopping when the token budget is reached
+
+Results are cached to disk (`~/.openclaude/repomap-cache/`) keyed by file path, mtime, and size. Only changed files are re-parsed on subsequent runs.
+
+## Supported languages
+
+- TypeScript (`.ts`, `.tsx`)
+- JavaScript (`.js`, `.jsx`, `.mjs`, `.cjs`)
+- Python (`.py`)
+
+Additional language grammars will be added in future releases.
+
+## Enabling auto-injection
+
+The repo map is gated behind the `REPO_MAP` feature flag, **off by default**. To enable auto-injection into the session context:
+
+Set the environment variable before launching:
+
+```bash
+REPO_MAP=1 openclaude
+```
+
+Or add it to your shell profile for persistent use.
+
+When enabled, the map is built once per session and prepended to the system context alongside git status and CLAUDE.md content. The default budget is 1024 tokens.
+
+Auto-injection is skipped in:
+- Bare mode (`--bare`)
+- Remote sessions (`CLAUDE_CODE_REMOTE`)
+
+## The /repomap slash command
+
+The `/repomap` command is always available regardless of the feature flag. It lets you inspect and tune the map interactively.
+
+```
+/repomap                          # Show the map with default settings (1024 tokens)
+/repomap --tokens 4096            # Increase the token budget for a larger map
+/repomap --focus src/tools/       # Boost specific paths in the ranking
+/repomap --focus src/context.ts   # Can use multiple --focus flags
+/repomap --stats                  # Show cache statistics
+/repomap --invalidate             # Clear cache and rebuild from scratch
+```
+
+## The RepoMap tool
+
+The model can also call the `RepoMap` tool on demand during a session. This is useful when:
+- The model needs structural context mid-conversation
+- The user asks about specific areas (the model can pass `focus_files` or `focus_symbols`)
+- A larger token budget is needed than the auto-injected default
+
+## Known limitations
+
+- **Signatures only** — The map shows function/class/type declarations, not implementations. The model still needs `Read` to see function bodies.
+- **Cold build time** — First build on large repos (2000+ files) can take 20-30 seconds due to WASM-based parsing. Subsequent builds use the disk cache and complete in under 100ms.
+- **Language coverage** — Only TypeScript, JavaScript, and Python are supported. Files in other languages are skipped.
+- **TypeScript references** — The TypeScript tree-sitter query captures type annotations and `new` expressions as references, but not plain function calls. This means the ranking slightly favors type-heavy hub files.
+- **Git dependency** — File enumeration uses `git ls-files` by default. Non-git repos fall back to a directory walk with hardcoded exclusions.

package.json

@@ -93,11 +93,15 @@
     "fflate": "0.8.2",
     "figures": "6.1.0",
     "fuse.js": "7.1.0",
+    "graphology": "^0.26.0",
+    "graphology-operators": "^1.6.0",
     "get-east-asian-width": "1.5.0",
     "google-auth-library": "9.15.1",
     "https-proxy-agent": "7.0.6",
     "ignore": "7.0.5",
+    "graphology-pagerank": "^1.1.0",
     "indent-string": "5.0.0",
+    "js-tiktoken": "^1.0.16",
     "jsonc-parser": "3.3.1",
     "lodash-es": "4.18.1",
     "lru-cache": "11.2.7",
@@ -117,10 +121,12 @@
     "strip-ansi": "7.2.0",
     "supports-hyperlinks": "3.2.0",
     "tree-kill": "1.2.2",
+    "tree-sitter-wasms": "^0.1.12",
     "turndown": "7.2.2",
     "type-fest": "4.41.0",
     "undici": "7.24.6",
     "usehooks-ts": "3.1.1",
+    "web-tree-sitter": "^0.25.0",
     "vscode-languageserver-protocol": "3.17.5",
     "wrap-ansi": "9.0.2",
     "ws": "8.20.0",

scripts/build.ts

@@ -36,6 +36,9 @@ const featureFlags: Record<string, boolean> = {
   COWORKER_TYPE_TELEMETRY: false, // Telemetry for agent/coworker type classification
   MCP_SKILLS: false,              // Dynamic MCP skill discovery (src/skills/mcpSkills.ts not mirrored; enabling this causes "fetchMcpSkillsForClient is not a function" when MCP servers with resources connect — see #856)
 
+  // ── Disabled by default, opt-in via runtime env var ─────────────────
+  REPO_MAP: false,                // Auto-injected codebase intelligence repo-map; users opt in with REPO_MAP=1 (the runtime gate in src/context.ts honors the env var even when this flag is false)
+
   // ── Enabled: upstream defaults ──────────────────────────────────────
   COORDINATOR_MODE: true,             // Multi-agent coordinator with worker delegation
   BUILTIN_EXPLORE_PLAN_AGENTS: true,  // Built-in Explore/Plan specialized subagents

src/commands.ts

@@ -23,6 +23,7 @@ import doctor from './commands/doctor/index.js'
 import onboardGithub from './commands/onboard-github/index.js'
 import knowledge from './commands/knowledge/index.js'
 import memory from './commands/memory/index.js'
+import repomap from './commands/repomap/index.js'
 import help from './commands/help/index.js'
 import ide from './commands/ide/index.js'
 import init from './commands/init.js'
@@ -311,6 +312,7 @@ const COMMANDS = memoize((): Command[] => [
   releaseNotes,
   reloadPlugins,
   rename,
+  repomap,
   resume,
   session,
   skills,

src/commands/repomap/index.ts

@@ -0,0 +1,17 @@
+/**
+ * /repomap command - minimal metadata only.
+ * Implementation is lazy-loaded from repomap.ts to reduce startup time.
+ */
+import type { Command } from '../../commands.js'
+
+const repomap = {
+  type: 'local',
+  name: 'repomap',
+  description:
+    'Show or configure the repository structural map (codebase intelligence)',
+  isHidden: false,
+  supportsNonInteractive: true,
+  load: () => import('./repomap.js'),
+} satisfies Command
+
+export default repomap

src/commands/repomap/repomap.test.ts

@@ -0,0 +1,56 @@
+import { describe, expect, test } from 'bun:test'
+import { parseArgs } from './repomap.js'
+
+describe('/repomap argument parsing', () => {
+  test('defaults to 1024 tokens with no flags', () => {
+    const result = parseArgs('')
+    expect(result.tokens).toBe(2048)
+    expect(result.focus).toEqual([])
+    expect(result.invalidate).toBe(false)
+    expect(result.stats).toBe(false)
+  })
+
+  test('parses --tokens flag', () => {
+    const result = parseArgs('--tokens 4096')
+    expect(result.tokens).toBe(4096)
+  })
+
+  test('rejects --tokens below 256', () => {
+    const result = parseArgs('--tokens 100')
+    expect(result.tokens).toBe(2048) // falls back to default
+  })
+
+  test('rejects --tokens above 16384', () => {
+    const result = parseArgs('--tokens 20000')
+    expect(result.tokens).toBe(2048) // falls back to default
+  })
+
+  test('parses --focus flag', () => {
+    const result = parseArgs('--focus src/tools/')
+    expect(result.focus).toEqual(['src/tools/'])
+  })
+
+  test('parses multiple --focus flags', () => {
+    const result = parseArgs('--focus src/tools/ --focus src/context.ts')
+    expect(result.focus).toEqual(['src/tools/', 'src/context.ts'])
+  })
+
+  test('parses --invalidate flag', () => {
+    const result = parseArgs('--invalidate')
+    expect(result.invalidate).toBe(true)
+    expect(result.stats).toBe(false)
+  })
+
+  test('parses --stats flag', () => {
+    const result = parseArgs('--stats')
+    expect(result.stats).toBe(true)
+    expect(result.invalidate).toBe(false)
+  })
+
+  test('parses combined flags', () => {
+    const result = parseArgs('--tokens 2048 --focus src/tools/ --invalidate')
+    expect(result.tokens).toBe(2048)
+    expect(result.focus).toEqual(['src/tools/'])
+    expect(result.invalidate).toBe(true)
+  })
+})

src/commands/repomap/repomap.ts

@@ -0,0 +1,93 @@
+import type { LocalCommandCall } from '../../types/command.js'
+import { getCwd } from '../../utils/cwd.js'
+
+/** Parse CLI-style arguments from the command string. */
+export function parseArgs(args: string): {
+  tokens: number
+  focus: string[]
+  invalidate: boolean
+  stats: boolean
+} {
+  const parts = args.trim().split(/\s+/).filter(Boolean)
+  let tokens = 2048
+  const focus: string[] = []
+  let invalidate = false
+  let stats = false
+
+  for (let i = 0; i < parts.length; i++) {
+    const part = parts[i]!
+    if (part === '--tokens' && i + 1 < parts.length) {
+      const n = parseInt(parts[i + 1]!, 10)
+      if (!isNaN(n) && n >= 256 && n <= 16384) {
+        tokens = n
+      }
+      i++
+    } else if (part === '--focus' && i + 1 < parts.length) {
+      focus.push(parts[i + 1]!)
+      i++
+    } else if (part === '--invalidate') {
+      invalidate = true
+    } else if (part === '--stats') {
+      stats = true
+    }
+  }
+
+  return { tokens, focus, invalidate, stats }
+}
+
+export const call: LocalCommandCall = async (args) => {
+  const root = getCwd()
+  const { tokens, focus, invalidate, stats } = parseArgs(args ?? '')
+
+  // Lazy import to avoid loading tree-sitter at startup
+  const {
+    buildRepoMap,
+    invalidateCache,
+    getCacheStats,
+  } = await import('../../context/repoMap/index.js')
+
+  if (stats) {
+    const cacheStats = getCacheStats(root)
+    const lines = [
+      `Repository map cache stats:`,
+      `  Cache directory: ${cacheStats.cacheDir}`,
+      `  Cache file: ${cacheStats.cacheFile ?? '(none)'}`,
+      `  Cached entries: ${cacheStats.entryCount}`,
+      `  Cache exists: ${cacheStats.exists}`,
+    ]
+    return { type: 'text', value: lines.join('\n') }
+  }
+
+  if (invalidate) {
+    invalidateCache(root)
+    const result = await buildRepoMap({
+      root,
+      maxTokens: tokens,
+      focusFiles: focus.length > 0 ? focus : undefined,
+    })
+    return {
+      type: 'text',
+      value: [
+        `Cache invalidated and rebuilt.`,
+        `Files: ${result.fileCount} ranked (${result.totalFileCount} total) | Tokens: ${result.tokenCount} | Time: ${result.buildTimeMs}ms | Cache hit: ${result.cacheHit}`,
+        '',
+        result.map,
+      ].join('\n'),
+    }
+  }
+
+  const result = await buildRepoMap({
+    root,
+    maxTokens: tokens,
+    focusFiles: focus.length > 0 ? focus : undefined,
+  })
+
+  return {
+    type: 'text',
+    value: [
+      `Repository map: ${result.fileCount} files ranked (${result.totalFileCount} total) | Tokens: ${result.tokenCount} | Time: ${result.buildTimeMs}ms | Cache hit: ${result.cacheHit}`,
+      '',
+      result.map,
+    ].join('\n'),
+  }
+}