@heart-of-gold/toolkit 0.1.18 → 0.1.20
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/package.json
CHANGED
|
@@ -79,8 +79,10 @@ Choose the permission mode based on what Claude Code needs to do:
|
|
|
79
79
|
When this skill is used from Codex, the skill cannot bypass Codex sandbox policy on its own. Instead, instruct Codex to choose the correct execution path:
|
|
80
80
|
|
|
81
81
|
- Prefer the direct `claude` command patterns in this skill. Do not silently substitute the bundled wrapper for the normal path just because it exists.
|
|
82
|
-
-
|
|
82
|
+
- In this environment, actual `claude -p` runs have been verified to hang inside the Codex sandbox but succeed outside it. Treat reviewer-approved elevated execution as the default practical path for real Claude invocations.
|
|
83
|
+
- Use the sandboxed path only when the user explicitly wants to test sandbox behavior or when you have a concrete reason to believe the sandbox limitation no longer applies.
|
|
83
84
|
- If Claude Code needs network access, auth refresh, access outside the writable sandbox, or the in-sandbox run fails or hangs for likely sandbox reasons, rerun via `exec_command` with `sandbox_permissions: "require_escalated"`.
|
|
85
|
+
- If you verify that direct `claude -p` works outside the sandbox but hangs inside it in the current environment, stop treating the sandboxed path as normal. For the rest of that Codex session, prefer reviewer-approved elevated execution as the default path for actual Claude invocations.
|
|
84
86
|
- Use a concise justification that tells the reviewer why Claude Code needs elevation, for example:
|
|
85
87
|
- "Do you want me to run Claude Code with network access so it can authenticate and complete this review?"
|
|
86
88
|
- "Do you want me to rerun Claude Code outside the sandbox because the in-sandbox headless run appears blocked by permissions?"
|
|
@@ -253,7 +255,9 @@ claude -r latest -p \
|
|
|
253
255
|
- If Claude Code hangs or times out, report that Claude did not complete in this environment. Do not continue with a self-authored substitute while implying it came from Claude.
|
|
254
256
|
- If Claude Code reports permission issues, choose the correct permission mode or constrain tools explicitly.
|
|
255
257
|
- If a headless run gets stuck on permissions, either switch to `plan`, use `acceptEdits`, or provide `--allowedTools` / a permission prompt tool.
|
|
258
|
+
- In this environment, prefer reviewer-approved elevated execution for real Claude runs instead of treating sandbox execution as the normal path.
|
|
256
259
|
- In Codex, if the likely cause is sandboxing or network denial, rerun with reviewer-approved `require_escalated` execution instead of repeatedly retrying the same sandboxed command.
|
|
260
|
+
- In Codex, if you have already confirmed that elevated execution works and sandboxed execution hangs, do not re-run the sandboxed path again during the same task.
|
|
257
261
|
- Do not use `bypassPermissions` unless the user explicitly approves it.
|
|
258
262
|
- If the direct `claude` path fails, report that failure directly. Do not route around it by pretending a wrapper run or a self-authored review is equivalent to Claude output.
|
|
259
263
|
- Do not automatically fall back to concatenating many files into stdin just because a direct Claude run failed once.
|
package/src/index.ts
CHANGED
|
@@ -7,7 +7,7 @@ import { targetsCommand } from "./commands/targets";
|
|
|
7
7
|
const main = defineCommand({
|
|
8
8
|
meta: {
|
|
9
9
|
name: "heart-of-gold",
|
|
10
|
-
version: "0.1.
|
|
10
|
+
version: "0.1.20",
|
|
11
11
|
description:
|
|
12
12
|
"Cross-platform installer for Heart of Gold skills — Codex, OpenCode, Pi, Claude Code, and more",
|
|
13
13
|
},
|