Plugins

Runtime-switchable model output styles with Claude Code outputStyles parity, plus the output.render.* presentation protocol: a /style command, per-session persistence, systemPrompt injection, six built-in styles, a web picker, and a renderer registry with per-session/per-tool rules and /export.

One-click Concise output style for DeepSeek Harness: results first, no filler, same work depth. Every final reply opens with a plain-language digest card (select text to copy), scoped per session, working in headless/CLI too, with /concise command, style.md overrides and a local API. Links and file paths inside the digest card render as clickable chips: URLs jump, local files open with the OS default app (v0.9+). A per-step pre-generation contract reminder (v0.11.2+) measurably fixes digest misses on audit-report/table-shaped replies.

Always-on ADHD-friendly output shaping: one system-prompt section makes replies action-first with numbered steps and concrete time estimates; adhd_on / adhd_off / adhd_status tools persist the mode across restarts.

ADHD-friendly output shaping where the mode belongs to one session, not a global setting: switch it with /i-have-adhd on|off in the conversations you want shaped, and the state stays with that session. Ported from ayghri/i-have-adhd.

Two split composer controls for output style: a tone switch with its own preset menu, and an output-form switch with its own preset menu; each session's system prompt follows the selections, with a preset settings page.

Persistent output styles for DeepSeek Harness Web: choose a built-in style or create named styles from the Settings page