nanocoai/nanoclaw / .claude/skills/add-onecli
add-onecli
FlaggedInstall or refresh OneCLI as NanoClaw's gateway provider. Use when setup selects OneCLI, an existing OneCLI-backed install is migrated to the gateway seam, or its runtime, approval bridge, setup, and agent guidance must be restored from the in-tree package.
references/chatgpt-oauth-refresh.md
View on GitHub# ChatGPT OAuth refresh with OneCLI
These notes apply to the current OneCLI credential adapter, not to any
provider's runtime contract.
OneCLI 1.42.0 could not refresh the ChatGPT OAuth credentials a provider
imports (for example OpenCode's ChatGPT sign-in): its refresh request omitted the
required client ID. OneCLI 1.43.1 sends it
([onecli/onecli#434](https://github.com/onecli/onecli/pull/434)), so the current
pin (1.45.0) includes the fix, but NanoClaw has not yet verified an unattended
refresh through it. Until it has, treat expiry as needing manual
reauthentication, for OpenCode the
[Recover a ChatGPT login](../../add-opencode/SKILL.md#recover-a-chatgpt-login) procedure.
The same procedure also handles revoked credentials.
A different proxy is not established as compatible by these tests.
The container holds only a fixed non-secret sentinel. Token refresh and account
metadata remain gateway responsibilities; never work around refresh failures by
copying live credentials into a group. Remove this version-specific note once
refresh through the pinned gateway has been verified.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |