Claude Code
How LinkCode runs Claude Code, including sign-in, the five approval policies, model and reasoning-effort switching, and shared thread history.
Claude Code is bundled with LinkCode's host (the LinkCode daemon) — there is nothing to install. Of the four supported agents, it has the most complete integration: a switchable approval policy, a curated model list, reasoning-effort control, and full thread history.
Sign in
LinkCode has no sign-in flow of its own for Claude Code. Two ways to authenticate:
- Reuse an existing
claudeCLI login. If you've already runclaude loginon this machine, LinkCode's bundled Claude Code reads the same credentials — no extra step. - Paste an Anthropic API key into Settings → Agents. LinkCode uses it only for threads started with this agent.
There's no dedicated auth-failure message today — a sign-in problem surfaces as a generic error on the thread.
Approval policy
Claude Code is the only agent with a real, switchable approval policy. Five policies are available, in this order:
| Policy | What it does |
|---|---|
| Ask permissions | Always asks before editing files and running commands. |
| Accept edits | Auto-approves file edits; still asks for everything else. |
| Plan mode | Read-only research; proposes a plan before making changes. |
| Auto mode | A classifier approves routine actions and blocks risky or external ones. |
| Bypass permissions | Skips all permission prompts in this workspace. |
You can switch policies at any point in a thread, and the change applies immediately. Not every policy is guaranteed to be available on every account — if a switch is rejected (for example, Auto mode or Bypass permissions on an account without the right entitlement), LinkCode keeps whatever policy was active before.
When you haven't picked a policy yet, Claude Code falls back to whatever permissions.defaultMode is set to in the closest settings file it finds, checked in this order:
.claude/settings.local.json(project, local to your machine).claude/settings.json(project)~/.claude/settings.json(your user settings)
This is the same precedence the standalone claude CLI uses. LinkCode only reads these files — it never writes to them.
For the difference between an approval policy (a standing setting) and a one-off permission prompt, see approvals.
Model and reasoning effort
Claude Code is the only agent with a curated model list in LinkCode:
- Opus 4.8
- Opus 4.7 (Legacy)
- Opus 4.6 (Legacy)
- Sonnet 5
- Sonnet 4.6 (Legacy)
- Haiku 4.5
It's also the only agent with reasoning-effort control: Low, Medium, High, xHigh, Max, and Ultracode. Model and effort both switch live, mid-thread, with one exception: switching to Max — the highest level — can't be applied to an already-running process, so LinkCode restarts the underlying Claude Code process and resumes your thread in place. There's a brief pause, but no lost context. The same restart happens when switching away from Max to any other level.
Ultracode additionally requires dynamic workflows to be enabled in your Claude configuration; if it isn't, the switch is rejected and your previous effort level stays selected.
Thread history
Claude Code threads in LinkCode read and write the same on-disk history the standalone claude CLI uses. A thread you start in LinkCode shows up in the claude CLI's own history, and a thread you started in the terminal can be opened and resumed from LinkCode. Stopping and resuming a thread is fully supported.