set-prompt 0.6.0 → 0.7.0

package/CHANGELOG.md

@@ -4,6 +4,30 @@ All notable changes to this project will be documented in this file.
 
 ---
 
+## [0.7.0] - 2026-04-20
+
+### Added
+- **OpenCode integration** (`link opencode`) — dir symlinks into `~/.config/opencode/` (OpenCode's default config directory). Links `skills/`, `commands/`, `agents/`.
+- **Gemini CLI integration** (`link geminicli`) — dir symlinks into `~/.gemini/` (coexists with Antigravity's `~/.gemini/antigravity/` subtree). Links `skills/`, `commands/`, `agents/`.
+- `OpencodeConfigSchema` / `GeminicliConfigSchema` + types + `configManager.opencode` / `configManager.geminicli` getter/setter + `isOpencodeEnabled()` / `isGeminicliEnabled()`
+- `SET_PROMPT_GUIDE` template: OpenCode frontmatter reference — skills (`name`, `description`, `license`, `compatibility`, `metadata`), commands (`template` required + `agent`/`model`/`subtask`), agents (`mode`, `temperature`, `top_p`, `steps`, `tools`, `permission`, `prompt` with `{file:...}` reference, etc.)
+- `SET_PROMPT_GUIDE` template: Gemini CLI frontmatter reference — skills (`name` + `description` — minimal), agents (`kind`, `tools` as array, `model`, `temperature` 0–2.0, `max_turns`, `timeout_mins`, `mcpServers` as nested YAML map), and a dedicated TOML sample for Gemini CLI commands (`prompt` required + `description`) with `{{args}}`/`!{cmd}`/`@{path}` placeholders and namespaced subdirectory support (`/git:commit`)
+- Tests: `tests/commands/link-opencode.test.ts`, `tests/commands/link-geminicli.test.ts`
+- README hero rewrite with `One repo. Every AI coding tool. Always in sync.` tagline, npm/GitHub/Sponsor badges, Quick Start section
+- `engines.node >=18` declared in `package.json`
+
+### Changed
+- `link-command.ts`: `LINK_MAP` / `UNLINK_MAP` / `prevLinked` extended with OpenCode and Gemini CLI entries
+- `checkbox` prompt UX: added `loop: false` and `pageSize: ALL_AGENTS.length` so the agent list no longer wraps around and shows all options without scrolling
+- Removed Contributing section from README (not accepting external PRs yet)
+
+### Notes / Caveats
+- **Gemini CLI commands use `.toml`** (not `.md`) — repo's `commands/` needs TOML files for Gemini to recognize them
+- **Gemini CLI agents have strict frontmatter validation** — rejects unknown keys (e.g. `color`, `allowed-tools`, `mode` from other platforms). Allowed keys only: `name`, `description`, `kind`, `tools`, `mcpServers`, `model`, `temperature`, `max_turns`, `timeout_mins`. Warning printed on link completion.
+- **RooCode skill directories must use hyphens, not underscores** — `my_skill` silently fails to register, `my-skill` works. Document-only gotcha (no code change); noted in `SET_PROMPT_GUIDE` skill `name` row.
+
+---
+
 ## [0.6.0] - 2026-04-14
 
 ### Added

package/README.md

@@ -1,12 +1,16 @@
 # Set Prompt
 
-As you work with AI agents, you build up your own prompt set — skills, commands, and workflows tailored to how you work.
-
-But every time you try a new AI agent, you have to set it all up again from scratch. And as your prompts evolve, keeping them in sync across multiple tools becomes a maintenance burden that the tools themselves don't help with.
+[![npm version](https://img.shields.io/npm/v/set-prompt?color=cb3837&logo=npm)](https://www.npmjs.com/package/set-prompt)
+[![npm downloads](https://img.shields.io/npm/dm/set-prompt?color=informational)](https://www.npmjs.com/package/set-prompt)
+[![GitHub stars](https://img.shields.io/github/stars/juncha9/set-prompt?color=f5d90a&logo=github)](https://github.com/juncha9/set-prompt/stargazers)
+[![last commit](https://img.shields.io/github/last-commit/juncha9/set-prompt?color=blueviolet&logo=github)](https://github.com/juncha9/set-prompt/commits/main)
+[![license](https://img.shields.io/npm/l/set-prompt?color=green)](./LICENSE.md)
+[![node](https://img.shields.io/node/v/set-prompt?color=success&logo=node.js)](https://nodejs.org)
+[![Sponsor](https://img.shields.io/badge/Sponsor-%E2%9D%A4-ea4aaa?logo=github-sponsors)](https://github.com/sponsors/juncha9)
 
-`set-prompt` was built to solve this. It maintains a single git repository of prompts and links them into each tool's expected location — so your prompt set stays in one place, stays versioned, and stays consistent across every AI agent you use.
+### One repo. Every AI coding tool. Always in sync.
 
-One repo. Every agent. Always in sync.
+Your skills, commands, and agents live in git. One command syncs them into every AI coding tool you use — so the prompts you built stay with you no matter which tool you're in.
 
 ```
                     repo/ (git)
@@ -23,21 +27,34 @@ One repo. Every agent. Always in sync.
         ┌──────────────────┼──────────────────────┐
         ▼                  ▼                       ▼
   Claude Code          Codex                  RooCode, OpenClaw,
-  (marketplace +       (marketplace +         Antigravity, Cursor
-   repo symlink)        cache symlink)        (dir symlinks)
+  (marketplace +       (marketplace +         Antigravity, Cursor,
+   repo symlink)        cache symlink)        OpenCode, Gemini CLI
+                                              (dir symlinks)
 ```
 
+## Quick Start
+
+From zero to linked in under a minute:
+
+```bash
+npm install -g set-prompt
+sppt install https://github.com/you/my-prompts   # or: sppt scaffold .
+sppt link                                        # interactive checkbox — pick your tools
+```
+
+That's it. Your prompts are now live in every AI tool you selected.
+
 ## Installation
 
 ```bash
+# global install (recommended)
 npm install -g set-prompt
-# or use without installing
+
+# one-off run without installing
 npx set-prompt <command>
 ```
 
-## CLI Alias
-
-`sppt` is a built-in short alias for `set-prompt` — all commands work with either name:
+Both `set-prompt` and the short alias `sppt` are registered — use whichever you prefer:
 
 ```bash
 sppt install <url>        # connect an existing repo
@@ -93,6 +110,8 @@ set-prompt link openclaw     # link OpenClaw only
 set-prompt link codex        # link Codex only
 set-prompt link antigravity  # link Antigravity only
 set-prompt link cursor       # link Cursor only
+set-prompt link opencode     # link OpenCode only
+set-prompt link geminicli    # link Gemini CLI only
 ```
 
 The interactive mode shows all agents with their current state. **Check to link, uncheck to unlink** — existing directories are backed up before being replaced.
@@ -105,13 +124,21 @@ The interactive mode shows all agents with their current state. **Check to link,
 | OpenClaw | dir symlinks into `~/.openclaw/workspace/` | `skills/` |
 | Antigravity | dir symlinks into `~/.gemini/antigravity/` | `skills/` |
 | Cursor | dir symlinks into `~/.cursor/` | `skills/`, `agents/`, `commands/`, `hooks/`, `mcp.json` (hardlink) |
+| OpenCode | dir symlinks into `~/.config/opencode/` | `skills/`, `commands/`, `agents/` |
+| Gemini CLI | dir symlinks into `~/.gemini/` | `skills/`, `commands/`, `agents/` |
 
 > **Note on Claude Code**: Operates as a plugin. Restart Claude Code after linking for the plugin to be recognized.
 
 > **Note on Codex**: Operates as a plugin. Restart Codex after linking — you may need to restart **twice** before the plugin is fully recognized.
 
+> **Note on RooCode**: Skill directory names must use hyphens only — `my_skill` (underscore) silently fails to be recognized, while `my-skill` works. Hyphens work on every platform, so default to them.
+
 > **Note on Cursor**: Does not load `rules/` from symlinked directories. Use `.cursor/rules/` within each project instead, or manage rules via Cursor Settings.
 
+> **Note on OpenCode**: Linked at `~/.config/opencode/` — OpenCode's default config directory, so no env var setup required.
+
+> **Note on Gemini CLI**: Skills follow the standard `skills/<name>/SKILL.md` pattern. Commands use `.toml` format (not `.md`) and agents use `.md` with YAML frontmatter. Files in your repo's `commands/` must be TOML for Gemini CLI to recognize them. **Agents have strict frontmatter validation** — unknown keys (e.g. `allowed-tools`, `color`, `mode` from other platforms) cause Gemini CLI to reject the agent. See `SET_PROMPT_GUIDE.md` for the allowed keys.
+
 ---
 
 ### Step 3 — Keep in sync
@@ -134,7 +161,7 @@ set-prompt repo path                  # print repo location (e.g. cd "$(sppt rep
 set-prompt repo open                  # open repo in OS file manager (--code VSCode, --stree Sourcetree)
 ```
 
-Symlink-based agents (Claude Code, Codex, RooCode, OpenClaw, Antigravity) reflect changes immediately after pull. Cursor's `mcp.json` is a hardlink to repo's `.mcp.json`, so edits to either side are reflected automatically.
+Symlink-based agents (Claude Code, Codex, RooCode, OpenClaw, Antigravity, OpenCode, Gemini CLI) reflect changes immediately after pull. Cursor's `mcp.json` is a hardlink to repo's `.mcp.json`, so edits to either side are reflected automatically.
 
 ---
 
@@ -209,6 +236,19 @@ set-prompt uninstall
 ├── commands/ → repo/commands
 ├── hooks/ → repo/hooks
 └── mcp.json ⇔ repo/.mcp.json  (hardlink)
+
+~/.config/opencode/          # OpenCode (dir symlinks)
+├── SET_PROMPT_BACKUP/
+├── skills/ → repo/skills
+├── commands/ → repo/commands
+└── agents/ → repo/agents
+
+~/.gemini/                   # Gemini CLI (dir symlinks)
+├── SET_PROMPT_BACKUP/
+├── skills/ → repo/skills       (Gemini reads SKILL.md)
+├── commands/ → repo/commands   (Gemini reads *.toml)
+├── agents/ → repo/agents       (Gemini reads *.md)
+└── antigravity/                (Antigravity's own subtree, unrelated)
 ```
 
 ## Warning
@@ -221,6 +261,8 @@ set-prompt uninstall
 - **OpenClaw** — replaces directories in `~/.openclaw/workspace/`
 - **Antigravity** — replaces directories in `~/.gemini/antigravity/`
 - **Cursor** — replaces directories and `mcp.json` in `~/.cursor/`
+- **OpenCode** — replaces directories in `~/.config/opencode/`
+- **Gemini CLI** — replaces directories in `~/.gemini/` (`antigravity/` subtree untouched)
 
 Before making any changes, `set-prompt` creates a backup and rolls back automatically on failure. However, you should be aware that:
 
@@ -242,9 +284,7 @@ Use `set-prompt uninstall` to cleanly revert all changes.
 - Star this repo
 - Report bugs — open an [issue](https://github.com/juncha9/set-prompt/issues) with steps to reproduce
 - Request features — share ideas via [issues](https://github.com/juncha9/set-prompt/issues)
-- Submit a PR — new agent integrations are welcome
-
-[![Sponsor](https://img.shields.io/badge/Sponsor-%E2%9D%A4-ea4aaa?logo=github-sponsors)](https://github.com/sponsors/juncha9)
+- [Sponsor on GitHub](https://github.com/sponsors/juncha9) if the project saves you time
 
 ## Dev Commands
 
@@ -256,13 +296,6 @@ npm unlink -g set-prompt         # Remove global CLI
 npm test                         # Run tests with vitest
 ```
 
-## Contributing
-
-> Contribution guidelines are still being figured out. For now, feel free to open an issue to discuss ideas or report bugs.
-
-- Bug reports and feature requests → [GitHub Issues](https://github.com/juncha9/set-prompt/issues)
-- PRs for new agent integrations are especially appreciated
-
 ## License
 
 This project is licensed under the [MIT License](./LICENSE.md).