auditor-lambda 0.3.11 → 0.3.12
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.
|
@@ -275,7 +275,7 @@ No dedicated Antigravity provider adapter is shipped today.
|
|
|
275
275
|
|
|
276
276
|
Current recommended usage is one of these:
|
|
277
277
|
|
|
278
|
-
- use the skill-first conversational contract as the primary surface
|
|
278
|
+
- use the skill-first conversational contract as the primary surface (note: do NOT use `browser_subagent` for semantic review of code unless explicitly required by the task)
|
|
279
279
|
- let `/audit-code` run `audit-code ensure --quiet`, or run `audit-code install` manually so compatibility files are present
|
|
280
280
|
- run `audit-code` from an Antigravity-managed terminal with `local-subprocess`
|
|
281
281
|
- use `subprocess-template` if you have a reliable Antigravity-side launcher bridge
|
package/package.json
CHANGED
|
@@ -28,6 +28,8 @@ and ingest results mechanically.
|
|
|
28
28
|
- CRITICAL: Do not use your `Read` tool to read `entry.prompt_path` or JSON schemas into your own context window. The subagent will read them. Pass the path literally.
|
|
29
29
|
- Prefer subagent dispatch for semantic review whenever the host exposes an
|
|
30
30
|
Agent/subagent tool.
|
|
31
|
+
- Do not use `browser_subagent` for semantic review of source code unless the
|
|
32
|
+
task explicitly requires browser-based validation.
|
|
31
33
|
- If the host cannot dispatch subagents, complete exactly one assigned review
|
|
32
34
|
task, run the provided ingestion command, then stop. The user can run
|
|
33
35
|
`/audit-code` again to continue from fresh context.
|