@mrciphersmith/keryx 0.3.118 → 0.3.119
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/cli.js +101101 -96529
- package/dist/core.js +1569 -1050
- package/package.json +1 -1
- package/src/gdgraph/service.ts +4 -0
- package/src/gdgraph/symbol-reach.ts +1069 -0
- package/src/gdskills/bundled/skills/orchestration/flow-orchestrator/SKILL.md +1 -1
- package/src/gdskills/bundled/skills/platform/scheduled-tasks/SKILL.md +2 -2
- package/src/gdskills/bundled/skills/review/review-orchestrator/SKILL.detail.md +68 -17
- package/src/gdskills/bundled/skills/review/review-orchestrator/SKILL.md +67 -67
- package/src/gdskills/bundled/skills/review/review-verifier/SKILL.md +3 -3
|
@@ -101,9 +101,9 @@ available, not the strongest one you can describe.**
|
|
|
101
101
|
|
|
102
102
|
### 1. `execution` — run something that fails if the finding is real
|
|
103
103
|
|
|
104
|
-
This is the method that works,
|
|
105
|
-
|
|
106
|
-
|
|
104
|
+
This is the method that works: the project's own test command on one file (`bun test <file>` where the project runs Bun, its `test` script otherwise), its type check, or a three-line script.
|
|
105
|
+
With no shell (a keryx shell child has none), the orchestrator runs it for you — `keryx review verify-run --package <review-dir> --finding <id> -- <command>` — and hands you the saved
|
|
106
|
+
`research-evidence/verify-<id>-<n>.txt`; cite that file as the evidence and the claim is recorded as executed. Without either, the method is not available.
|
|
107
107
|
|
|
108
108
|
The test is not "does the suite pass". It is: **construct the situation the
|
|
109
109
|
finding claims is broken, and see whether it breaks.**
|