@abdulmunimjemal/codescope 0.1.0 → 0.3.0

package/README.md

@@ -28,15 +28,20 @@ a changed file in **~0.5 ms** — roughly **3,000× cheaper than a full re-index
 
 ## How it compares to codegraph
 
-If you know [codegraph](https://github.com/colbymchenry/codegraph) (~35k★): it's
-the mature, feature-rich option — 20+ languages, impact/test-affected analysis, a
-task-context builder, agent auto-install — and it already does incremental
-indexing and file-watching. **codescope doesn't try to out-feature it.** In a
-measured head-to-head ([BENCHMARKS.md](./BENCHMARKS.md)) codescope's edge is being
-**leaner**: ~3× smaller index DB and faster pure indexing on the same repo, a
-~1k-LOC auditable codebase, and zero-config `npx codescope mcp .`. Pick codescope
-if you want something small, fast, and easy to read; pick codegraph if you want
-the deepest feature set and widest language coverage.
+[codegraph](https://github.com/colbymchenry/codegraph) (~35k★) is the mature
+incumbent and shares codescope's architecture. In a **measured head-to-head**
+([BENCHMARKS.md](./BENCHMARKS.md), both tools run on the same repos), codescope
+**wins the efficiency axes**:
+
+- **~4× faster indexing** (696 ms vs 2,855 ms on a 262-file repo; 5.2 s vs 20 s on 3,500 files).
+- **3–5× smaller index** on disk (2.5 MB vs 8.2 MB; 22.9 MB vs 112.8 MB).
+- **Fewer tokens per answer** for definition lookups on every repo tested; callers is ≈parity.
+- **Feature parity:** `callers`, `callees`, `impact`, `context`, **`affected`** (test-impact), and **`install`** (agent auto-wiring) — plus **20 languages**.
+
+codegraph still leads on **maturity & adoption** (35k★, a real user base) and
+indexes a few extra node kinds (constants, properties, routes). Pick codescope
+when footprint, index speed, and token cost matter; pick codegraph for the most
+battle-tested option.
 
 ## Install
 
@@ -50,11 +55,20 @@ collides with an existing package; the installed command is still `codescope`.)
 
 ## Quick start
 
-Point your agent at codescope as an MCP server. It indexes the repo, starts
-watching for changes, and serves the graph over stdio:
+The one-liner — wire codescope into your agents automatically, from your repo:
+
+```bash
+npx @abdulmunimjemal/codescope install     # adds codescope to Claude Code + Cursor
+```
+
+That writes the MCP server config (non-destructively) so your agent launches
+codescope on the repo. Restart the agent and you're done. `--agent claude|cursor`
+targets one; `--global` writes to your home dir instead of the project.
+
+Prefer to wire it by hand? The server command is:
 
 ```bash
-codescope mcp /path/to/your/repo
+codescope mcp /path/to/your/repo            # index, watch, and serve over stdio
 ```
 
 **Claude Code** (`.mcp.json` or `claude mcp add`):
@@ -77,6 +91,10 @@ codescope index .                       # build the graph, print stats
 codescope search useState               # fuzzy symbol search
 codescope get GraphStore                # jump to a definition
 codescope callers parseSource           # who calls this
+codescope callees indexAll              # what it calls
+codescope impact GraphStore             # blast radius before a change
+codescope context "auth flow"           # ranked relevance map for a task
+codescope affected src/store.ts         # which tests are affected by a change
 codescope neighborhood handleRequest --depth 3
 codescope watch .                       # keep the graph fresh, log updates
 ```
@@ -87,7 +105,10 @@ codescope watch .                       # keep the graph fresh, log updates
 |------|-----------------|
 | `search_symbols(query, kind?, limit?)` | fuzzy substring search over definitions — use instead of grep/glob |
 | `get_symbol(name, limit?)` | jump to a definition by exact name (kind, `file:line`, signature) |
-| `find_callers(name, limit?)` | who calls this function/method |
+| `find_callers(name, limit?)` | who calls this function/method (distinct callers) |
+| `find_callees(name, limit?)` | what this symbol calls — its outgoing dependencies |
+| `impact(name, depth?, limit?)` | transitive callers (blast radius) before you change something |
+| `context(query, maxSymbols?)` | a ranked relevance map for a task — matches + neighbours, the fastest way to orient |
 | `find_references(name, kind?, limit?)` | all calls + imports of a name |
 | `file_outline(path)` | every symbol in a file, in order — a compact alternative to reading it |
 | `neighborhood(name, depth?, limit?)` | the call neighbourhood (callers + callees) around a symbol, as a subgraph |
@@ -119,7 +140,10 @@ The index lives in `.codescope/graph.db` (add `.codescope/` to your
 
 ## Languages
 
-TypeScript, JavaScript, TSX/JSX, Python, Go, Rust, Java, Ruby, C, C++, C#, PHP.
+20 languages: TypeScript, JavaScript, TSX/JSX, Python, Go, Rust, Java, Ruby, C,
+C++, C#, PHP, Scala, Solidity, Zig, Kotlin, Objective-C, Lua, Bash, and OCaml.
+Definition extraction (functions, classes, methods, …) works for all; call and
+import edges are available for the languages whose grammars expose them.
 
 ## Programmatic API