ex-machina-co/opencode-anthropic-auth/sync-main-to-v2

Claude Code and agent skill by ex-machina-co/opencode-anthropic-auth

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Install

npx vskill@latest install ex-machina-co/opencode-anthropic-auth/sync-main-to-v2

SKILL.md

Syncing main into v2/main

This skill does not describe the synchronization workflow. The workflow lives in one place: the companion file references/plan.md, beside this skill. That file is a complete VIPER plan and is the canonical source of truth. This skill only explains how to materialize it and run it.

Load viper-execution-rules before executing anything.

Prerequisites

The viper-plans facet must be installed in the project. It supplies the execution rules and the plan tools. If neither the plan tools nor .opencode/plans/ are available, say so and stop — do not improvise a substitute workflow.

Plan tools

The viper-plans MCP server provides viper-write-plan, viper-read-plan, viper-edit-plan, viper-list-plans, and viper-delete-plan. A client may expose them under a prefixed name such as viper-plans_viper-write-plan, so treat any tool whose name ends with one of those canonical names as that tool. Prefer them whenever they are available; otherwise use the file-tool fallback noted below.

Procedure

  1. Read the canonical plan. Read references/plan.md relative to this skill's own directory, as

reported when the skill was loaded. Read it in full.

  1. Materialize it as the runtime plan. Persist that exact content under the plan name

main-to-v2-sync, using viper-write-plan if available; otherwise write .opencode/plans/main-to-v2-sync/plan.md with your file tools, creating the directory if needed.

Overwrite any existing plan of that name without asking. The plan store holds a generated copy, not the source. Never edit references/plan.md to reflect a runtime decision, and never merge a stale runtime copy back into it.

  1. Execute it immediately. Count the ### Step headings, state the plan name and step count in

one line, then follow the viper-execution-rules protocol: one TODO per step heading, steps in document order, Propose and Review steps gated on the user, and a stop on any Verify failure.

Do not add an outer approval cycle around the plan. The plan carries its own Propose and Review gates, and an invocation of the command is authorization to begin it.

  1. Do not delete the runtime plan at the end of the run unless the user asks. It is cheap to

regenerate and useful to inspect.

Authority

The plan is authoritative over this skill and over the command that loads it. If the plan and any prose here appear to disagree, the plan wins, and the disagreement is a bug in this facet worth reporting to the user.

Beginning the run authorizes only what the plan authorizes: it prepares and verifies a local branch. Pushing that branch or opening a pull request happens only through the plan's own explicit user gate. Nothing in this facet ever merges a pull request or publishes a package.

Security

  • Security scanPassed, 93 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
524
Repository forks
69
7-day trend score
31

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/ex-machina-co/opencode-anthropic-auth/sync-main-to-v2/badge)](https://verified-skill.com/skills/ex-machina-co/opencode-anthropic-auth/sync-main-to-v2)

Something wrong with this skill or its page? Tell us.