vp-debug

Name: vp-debug
Author: 0-CODE

Engineering Verified v0.2.0

Repo stars 13
Author updated Live
Author repo viepilot

Fluxly profile Facts only: domain, agents, trust score, runtime, permissions and network

Domain: Engineering
Compatible agents: Claude Code
Cursor
Cline
Codex
Windsurf
Gemini CLI

+20
Trust score: 92 / 100 · audit passed
Author / version / license: @0-CODE · v0.2.0 · no license declared
Token usage: Lean
Setup complexity: Guided setup
External API key: Not required
Operating systems: macOS · Linux · Windows
Runtime requirements: Node.js
Permissions: Read-only
Write / modify
Shell exec
Network behavior: Local-only
Install commands: 26 variants

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview vp-debug.preview

---
name: vp-debug
description: Systematic debugging with persistent state tracking across sessions Use when available; do not b…
category: engineering
runtime: Node.js
---

# vp-debug output preview

## PART A: Task fit
- Use case: Systematic debugging with persistent state tracking across sessions Use when available; do not block debug flow if missing. Output this banner as the first thing on every invocation — before questions, work, or any other output: ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ VIEPILOT ► VP-DEBUG v0.2.0 (fw 2.19.0) runs entirely locally; runs on Node.js. Works wit….
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Invocation Banner / Version Update Check (ENH-072) / Persona Context Injection (ENH-073)” and do not present inference as author intent.

## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Systematic debugging with persistent state tracking across sessions Use when available; do not block debug flow if missing. Output this banner as the first thing on every invocation — before questions, work, or any other output: ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ VIEPILOT ► VP-DEBUG v0.2.0 (fw 2.19.0) runs entirely locally; runs on Node.js. Works wit…”.
- **02** When the source has headings, the agent prioritizes “Invocation Banner / Version Update Check (ENH-072) / Persona Context Injection (ENH-073)” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.

## Running Rules
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.

SKILL.md SKILL.md

---
name: vp-debug
description: Systematic debugging with persistent state tracking across sessions Use when available; do not b…
category: engineering
source: 0-CODE/viepilot
---

# vp-debug

## When to use
- Systematic debugging with persistent state tracking across sessions Use when available; do not block debug flow if mis…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.

## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.

## Execution rules
- Organize steps around “Invocation Banner / Version Update Check (ENH-072) / Persona Context Injection (ENH-073)” and keep inference separate from source facts.
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.

## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.

Evidence boundary and execution chain

The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.

skill "vp-debug" {
  input      -> user goal + target files + boundaries + acceptance criteria
  context    -> Invocation Banner / Version Update Check (ENH-072) / Persona Context Injection (ENH-073)
  rules      -> SKILL.md triggers / order / output contract
  runtime    -> Node.js | read files, write/modify files, run shell commands | mostly runs locally
  guardrails -> usually needs no extra API key + small-sample validation + diff/log review
  output     -> copyable result + checklist + next iteration
}

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: Systematic debugging with persistent state tracking across sessions Use when available; do not block debug flow if missing. Outp…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “Invocation Banner”, “Version Update Check (ENH-072)”, “Persona Context Injection (ENH-073)”, “A. Skill Invocation”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name vp-debug directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “Invocation Banner / Version Update Check (ENH-072) / Persona Context Injection (ENH-073)” before expanding.

Boundaries And Review

Dependencies: It usually needs no extra API key, so start with a small validation task.
Permissions: Declared permissions include read / write / shell-exec; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

## Invocation Banner

Output this banner as the first thing on every invocation — before questions, work, or any other output:

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 VIEPILOT ► VP-DEBUG  v0.2.0 (fw 2.19.0)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

## Version Update Check (ENH-072)

After displaying the greeting banner, run:

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)

## 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. ## A. Skill Invocation - Skill được gọi khi user mention `vp-debug`, `/vp-debug`, "debug", "gỡ lỗi" - Treat all user text after the skill mention as `{{VP_ARGS}}`

B. User Prompting

Prompt user conversationally. Guide through systematic debugging steps.

C. 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)

## 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

## 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.

## 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

## 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

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.

## Implementation routing guard (ENH-021)

Investigate + log session; does not merge default shipping fixes until user explicit (fix now, hotfix) or routes /vp-request → /vp-evolve → /vp-auto. Small patches only to reproduce are OK if the user agrees. See workflows/debug.md.

Systematic debugging with persistent state tracking. Helps track issues across multiple sessions.

Creates/Updates:

.viepilot/debug/session-{id}.json - Debug session state
.viepilot/debug/CURRENT.json - Active session pointer

Modes:

new - Start new debug session
continue - Continue current session
list - List all sessions
close - Close current session with resolution

Architecture diagram intake (ENH-018):

If .viepilot/ARCHITECTURE.md has diagram applicability matrix, consume it before deep debugging.
Prioritize investigation context from diagrams marked required.
For optional diagrams: use when available; do not block debug flow if missing.
For N/A diagrams: respect rationale and avoid forcing diagram creation during debug.

@$HOME/{envToolDir}/workflows/debug.md Optional flags: - `--new` : Force new session - `--continue` : Continue current session - `--list` : List all sessions - `--close [resolved|unresolved|wontfix]` : Close session - `--id ` : Work with specific session Execute workflow from `@$HOME/{envToolDir}/workflows/debug.md`

Debug Session Structure

{
  "id": "debug-{timestamp}",
  "status": "active|resolved|unresolved|wontfix",
  "created_at": "ISO timestamp",
  "updated_at": "ISO timestamp",
  "problem": {
    "description": "User's problem description",
    "symptoms": ["symptom1", "symptom2"],
    "error_messages": ["error1"],
    "affected_files": ["file1.js"]
  },
  "investigation": {
    "hypotheses": [
      {"id": 1, "description": "...", "status": "testing|confirmed|rejected"}
    ],
    "tests_run": [
      {"command": "...", "output": "...", "timestamp": "..."}
    ],
    "findings": ["finding1", "finding2"]
  },
  "resolution": {
    "root_cause": "Description of root cause",
    "fix_applied": "Description of fix",
    "files_changed": ["file1.js"],
    "verification": "How it was verified"
  }
}

Key Steps

Start Session: Gather problem description
Load Architecture Context: Read .viepilot/ARCHITECTURE.md matrix status (required|optional|N/A) and relevant Mermaid diagrams if present
Hypothesize: Generate possible causes
Test: Run tests to confirm/reject hypotheses
Track: Log all findings
Resolve: Document fix and root cause
Close: Mark session complete

- [ ] Session created with problem description - [ ] Hypotheses tracked with status - [ ] Tests logged with outputs - [ ] Findings documented - [ ] Resolution recorded (if resolved) - [ ] State persists across sessions

Install command

One-click installPick a runner, click Copy, paste into your terminal, press enter

npx skills add 0-CODE/viepilot/skills/vp-debug -y

Open general install guide

View skill source

Works with

Claude Code
Cursor
Cline
Codex
Windsurf
Gemini
OpenCode
Roo Code
AAide
+Augment
GitHub Copilot
OpenClaw
KKiro
Junie
WWarp
Goose
Trae
Kilo Code
OpenHands
Amp
Zencoder
CContinue
AIAider
CodeBuddy
CodeGeeX
Replit Agent

Security audit

92 / 100

Verified

未声明 license/许可。
未限定 allowed-tools，默认拥有全部工具权限。

Metadata

Source: github
0-CODE/viepilot
Version: 0.2.0
中文

More by @0-CODE

Category & tags

Category Engineering

Decide Fit First

Design Intent

How To Use It

Boundaries And Review

B. User Prompting

C. Tool Usage

C. Tool Usage

C. Tool Usage

C. Tool Usage

C. Tool Usage

ViePilot Namespace Guard (BUG-004)

Debug Session Structure

Key Steps

Discussion