vp info
- Repo stars 13
- Author repo viepilot
- Domain
- Engineering
- Author-declared agents
- No explicit declaration found; this is not inferred or tested compatibility
- Static check
- 92 / 100 · heuristic scan, not runtime safety proof
- Runtime evidence
- Not run; no isolated runtime test evidence is currently recorded
- Author / version / license
- @0-CODE · v0.1.1 · no license declared
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Not required
- Operating systems
- macOS · Linux · Windows
- Runtime requirements
- Node.js
- Detected file/system behavior
-
- Read-only
- Write / modify
- Shell exec
- Network behavior
- Local-only
- Install commands
- None (reference only)
Heads up: Tool permissions are not declared; actual access depends on the runtime.
Priority order: `vp-tools info` — when ViePilot is already on `PATH` (npm global or shim). `node <viepilot-package>/bin/vp-tools.cjs info` — from repo clone or `node_modules/viepilot`.
Step 2: Run command
`packageRoot`: root of the `viepilot` package the CLI resolved. `installedVersion`: semver in `package.json` of that bundle. `latestNpm`: `{ ok, version }` or `{ ok: false, error }`. `skills`: skill inventory in `skills/*/SKILL.md` (version from frontmatter). `workflows`: files in `workflows/*.md`.
If package root is not found: install globally (`npm i -g viepilot`), or run from a project that has `viepilot` as a dependency, or point directly to `bin/vp-tools.cjs` in a clone. </process> <success_criteria> [ ] Correct subcommand `info` called (or `--json` when parsing is needed) [ ] `installedVersion` and (if available) `latestNpm.version` clearly stated
<greeting>
## Invocation Banner
Output this banner as the **first** thing on every invocation — before questions, work, or any other output:
```
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
VIEPILOT ► VP-INFO v0.1.1 (fw 2.19.0)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
```
</greeting>
<version_check>
## Version Update Check (ENH-072)
After displaying the greeting banner, run:
```bash
node "$HOME/.claude/viepilot/bin/vp-tools.cjs" check-update --silent
```
**If exit code = 1** (update available — new version printed to stdout):
Display notice banner before any other output:
```
┌──────────────────────────────────────────────────────────────────┐
│ ✨ ViePilot {latest_version} available (installed: {current}) │
│ npm i -g viepilot && vp-tools install --target {adapter_id} │
└──────────────────────────────────────────────────────────────────┘
```
Replace `{latest_version}` with stdout from the command, `{current}` with the installed
version, `{adapter_id}` with the active adapter (claude-code / cursor / antigravity / codex / copilot).
**If exit code = 0 or command unavailable**: silent, continue.
**Suppression rules:**
- `--no-update-check` flag on skill invocation → skip this step entirely
- `config.json` → `update.check: false` → skip this step entirely
- Show at most once per session (`update_check_done` session guard)
</version_check>
<persona_context>
## Persona Context Injection (ENH-073)
At skill start, run:
```bash
node "$HOME/.claude/viepilot/bin/vp-tools.cjs" persona auto-switch
node "$HOME/.claude/viepilot/bin/vp-tools.cjs" persona context
```
Inject the output as `## User Persona` context before any task execution.
Silent if command unavailable or errors.
</persona_context>
<adapter id="claude-code">
## A. Skill Invocation
- Skill được gọi khi user mention `vp-info`, `/vp-info`, "viepilot version", "phiên bản viepilot", "skills list bundle"
- Treat all user text after the skill mention as `{{VP_ARGS}}`
## B. Tool Usage
Use Claude Code tools: `Bash` (shell), `Read` (file), `Edit` + `Write` (file write/patch),
`Grep` (search), `Glob` (file patterns), `LS`, `WebSearch`, `WebFetch`,
`Agent` (spawn subagent — multi-level nesting supported)
Interactive: `AskUserQuestion` (deferred — preload via ToolSearch before first call)
</adapter>
<adapter id="cursor-agent">
## A. Skill Invocation
Same trigger keywords as claude-code adapter.
## C. Tool Usage
Use Cursor tools: `run_terminal_cmd` (shell), `read_file` (read), `edit_file` (write/edit),
`grep_search` (search), `web_search`, `codebase_search`, `list_dir`, `file_search`
Interactive: text list fallback (AskQuestion available in Plan Mode only; Agent Mode = text)
Subagent: `/multitask` (user command, single-level only — not a callable tool)
MCP limit: 40 tools
</adapter>
<adapter id="antigravity">
## A. Skill Invocation
Same trigger keywords as claude-code adapter.
Skill discovery: LLM-driven (automatic, no slash command needed).
## C. Tool Usage
Use Antigravity tools: `shell` (cmd), `file_read`, `file_write`, MCP plugins
Interactive: text fallback (TUI-based; no formal AskUserQuestion)
Skill path: `.agents/skills/<skill>/SKILL.md` (project) or `~/.gemini/antigravity/skills/` (global)
Note: Gemini CLI deprecated June 18, 2026 — use Antigravity CLI.
</adapter>
<adapter id="codex">
## A. Skill Invocation
Same trigger keywords as claude-code adapter.
## C. Tool Usage
Use Codex tools: `container.exec` (sandboxed shell), `apply_patch` (file write), `web_search`
Interactive: text fallback (TUI Tab/Enter injection)
Config: `~/.codex/config.toml`
</adapter>
<adapter id="copilot">
## A. Skill Invocation
Same trigger keywords as claude-code adapter.
Discovery: User-driven (`@agent-name` in GitHub Copilot Chat).
## C. Tool Usage
Use Copilot tools: `runCommands` (shell), `read`/`readfile` (read), `edit`/`editFiles` (write),
`code_search`, `find_references`
Interactive: `askQuestions` (main agent only — NOT available in subagents; VS Code issue #293745)
Skill path: `.github/agents/<name>.agent.md`
</adapter>
<scope_policy>
## ViePilot Namespace Guard (BUG-004)
- Default mode: only use and reference `vp-*` skills in ViePilot workflows.
- External skills (`non vp-*`) are out of framework scope unless user explicitly opts in.
- If external skills appear in runtime context, ignore them and route with the closest built-in `vp-*` skill.
</scope_policy>
<implementation_routing_guard>
## Implementation routing guard (ENH-021)
- **Inventory / version info** — does not implement shipping; implement via **`/vp-auto`**. See `workflows/request.md`.
</implementation_routing_guard>
<objective>
Run **`vp-tools info`** to retrieve the ViePilot bundle metadata (no `.viepilot/` needed in the target project).
**Useful output for agents:**
- `installedVersion`, `packageName`, `packageRoot`
- `latestNpm` (ok + version or network/registry error)
- `gitHead` (if clone has git)
- `skills[]`: `id`, `version`, `relativePath`
- `workflows[]`: `id`, `relativePath`, `note`
Use **`vp-tools info --json`** when parsing or comparing versions in scripts.
</objective>
<execution_context>
@$HOME/{envToolDir}/bin/vp-tools.cjs
</execution_context>
<process>
### Step 1: Resolve CLI
Priority order:
1. `vp-tools info` — when ViePilot is already on `PATH` (npm global or shim).
2. `node <viepilot-package>/bin/vp-tools.cjs info` — from repo clone or `node_modules/viepilot`.
### Step 2: Run command
```bash
vp-tools info
# or
vp-tools info --json
```
### Step 3: Interpret JSON (when using `--json`)
- **`packageRoot`**: root of the `viepilot` package the CLI resolved.
- **`installedVersion`**: semver in `package.json` of that bundle.
- **`latestNpm`**: `{ ok, version }` or `{ ok: false, error }`.
- **`skills`**: skill inventory in `skills/*/SKILL.md` (version from frontmatter).
- **`workflows`**: files in `workflows/*.md`.
### Step 4: Common errors
If package root is not found: install globally (`npm i -g viepilot`), or run from a project that has `viepilot` as a dependency, or point directly to `bin/vp-tools.cjs` in a clone.
</process>
<success_criteria>
- [ ] Correct subcommand `info` called (or `--json` when parsing is needed)
- [ ] `installedVersion` and (if available) `latestNpm.version` clearly stated
- [ ] When user asks “what skills are in the bundle”, summarize from `skills[]` or CLI table output
</success_criteria>
Listed in source order.
sections -> Invocation Banner → Version Update Check (ENH-072) → Persona Context Injection (ENH-073) → A. Skill Invocation → B. Tool Usage → C. Tool Usage
terms -> first · If exit code = 1 · If exit code = 0 or command unavailable · Suppression rules · Inventory / version info · /vp-auto · vp-tools info · Useful output for agents
files/cmd -> {latest_version} · {current} · {adapter_id} · --no-update-check · config.json · update.check: false · update_check_done · ## User Persona
body sha256 -> 5af82740dbe2
Invocation Banner
Output this banner as the first thing on every invocation — before questions, work, or any other output: </greeting> <version_check>
Version Update Check (ENH-072)
After displaying the greeting banner, run: If exit code = 1 (update available — new version printed to stdout): Display notice banner before any other output: Replace
{latest_version}with stdout from the command,{current}with the installed version,{adapter_id}with the active adapter (claude-code / cursor / antigravity / codex / copilot).Persona Context Injection (ENH-073)
At skill start, run: Inject the output as
## User Personacontext before any task execution. Silent if command unavailable or errors. </persona_context> <adapter id="claude-code">B. Tool Usage
Use Claude Code tools:
Bash(shell),Read(file),Edit+Write(file write/patch),Grep(search),Glob(file patterns),LS,WebSearch,WebFetch,Agent(spawn subagent — multi-level nesting supported) Interactive:AskUserQuestion(deferred — preload via ToolSearch before first call) </adapter>C. Tool Usage
Use Cursor tools:
run_terminal_cmd(shell),read_file(read),edit_file(write/edit),grep_search(search),web_search,codebase_search,list_dir,file_searchInteractive: text list fallback (AskQuestion available in Plan Mode only; Agent Mode = text) Subagent:/multitask(user command, single-level only — not a callable tool) MCP limit: 40 tools