@dotdotgod/codex 0.1.18 → 0.1.19

package/README.md

@@ -4,17 +4,28 @@
 
 > **Change a file, know what else must be checked.**
 
-Codex adapter for dotdotgod's context curation workflow. It packages reusable skills that help Codex initialize shared agent docs, load bounded project memory, and plan from docs before implementation.
-
-Impact/context in practice:
+```bash
+$ dotdotgod graph impact . --changed packages/cli/src/core.mjs --compact
+```
 
 ```text
-dd:init creates the memory scaffold
-dd:load reads a bounded snapshot and relevant docs
-dd:plan captures durable task intent before implementation
+docs:
+- docs/spec/REFERENCE_EXPANSION.md (91; incoming:implemented_by, semantic_similarity)
+- docs/test/REFERENCE_EXPANSION.md (65.3; verified_by, semantic_similarity)
+- docs/spec/LOAD_PROJECT.md (35.8; related_doc, semantic_similarity)
+
+tests:
+- packages/cli/test/core.test.mjs (78.6; semantic_similarity, incoming:semantic_similarity, verified_by)
+- packages/cli/test/e2e.test.mjs (51.4; verified_by)
+
+files:
+- packages/cli/src/core.mjs (100; changed-file)
+- packages/pi/extensions/plan-mode/index.ts (45; implemented_by, semantic_similarity)
 ```
 
-The same project-memory graph that powers `dotdotgod graph impact` can surface likely related docs, tests, source, and config for changed files. The graph is not only traceability: it also uses Markdown links, README routes, headings, package metadata, memory-area membership, commands, tests, and deterministic routing hints.
+`graph impact` ranks the specs, tests, architecture notes, config docs, and source files most likely to matter for a change. `--compact` keeps the result agent-facing: grouped by docs/tests/files and annotated with the reasons each item is likely relevant. It uses the project-memory graph built from Markdown links, README routes, headings, traceability blocks, package metadata, memory areas, and deterministic routing hints.
+
+Codex adapter for dotdotgod's context curation workflow. It packages reusable skills that help Codex initialize shared agent docs, load bounded project memory, and plan from docs before implementation.
 
 ## What Gets Better?
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@dotdotgod/codex",
-  "version": "0.1.18",
+  "version": "0.1.19",
   "description": "Codex adapter for dotdotgod project memory workflows.",
   "type": "module",
   "license": "MIT",