promptwheel 0.7.4 → 0.7.6

package/package.json

@@ -1,17 +1,19 @@
 {
   "name": "promptwheel",
-  "version": "0.7.4",
+  "version": "0.7.6",
   "description": "A deterministic, zero-LLM check for your coding loop. It proves every change earned its win by re-running the result from the agent's source edits alone, so a green that came from editing the test reads GAMED. Runs in CI or a Claude Code hook, or import { check } in process.",
   "type": "module",
   "bin": {
-    "promptwheel": "bin/promptwheel.mjs",
-    "pw": "bin/promptwheel.mjs"
+    "promptwheel": "bin/promptwheel.mjs"
   },
+  "types": "./bin/promptwheel.d.ts",
   "exports": {
-    ".": "./bin/promptwheel.mjs",
+    ".": {
+      "types": "./bin/promptwheel.d.ts",
+      "default": "./bin/promptwheel.mjs"
+    },
     "./bin/promptwheel.mjs": "./bin/promptwheel.mjs",
-    "./package.json": "./package.json",
-    "./packs/*": "./packs/*"
+    "./package.json": "./package.json"
   },
   "files": [
     "bin",

package/packs/security/README.md

@@ -9,18 +9,28 @@ lower the count by editing the pattern file or a config, only by fixing the code
 
 ## Use it
 
-In your `promptwheel.config.json`:
+The pack ships inside the `promptwheel` package, not in your repo, so install it with the
+preset:
 
-```json
-{ "extends": ["packs/security/pack.json"] }
+```bash
+promptwheel init --preset security            # or --preset security-antihack, which adds the tripwires
 ```
 
-Then gate as usual:
+`init` copies the pack into `.promptwheel/packs/security/` and writes a `security_findings`
+metric that runs it from there. Commit the pack with the config: the gate measures in clean
+git worktrees, so a pack that is not in git is absent at both refs and the metric reads
+`unmeasurable` (init warns when `.promptwheel/` is gitignored; change that rule to
+`.promptwheel/*` plus `!.promptwheel/packs/`, since git cannot re-include a file under an
+ignored directory). Then gate as usual:
 
 ```bash
 promptwheel run --working          # fails if security_findings increased
 ```
 
+`pack.json` is the same metric as a config fragment for `extends`
+(`{ "extends": ["packs/security/pack.json"] }`); its command is relative to a repo that
+holds the pack at `packs/security/`, such as a vendored copy or this repository.
+
 A finding-count that drops because you fixed the code is a `PASS`; a "fix" that
 only survives with test/config/pattern edits reverted is `GAMED`.
 
@@ -46,7 +56,7 @@ Each pattern ships with its own false-positive guards (the `exclude` regexes).
 
 This is the **regex-portable** slice. The other ~75 recommended invariants
 (auth-enforcement, authz-revocation, tenant-isolation, dataflow-tainted sinks)
-need the AST + dataflow engine and are the follow-up - see the decant note in
-`explorations/`. The point of v0.1 is the architecture: security invariants are
+need an AST + dataflow engine and are a possible follow-up, not part of this
+pack. The point of v0.1 is the architecture: security invariants are
 now a first-class, un-gameable PromptWheel metric. Zero dependencies; the scanner
 is one file (`scan.mjs`).