Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add darellchua2/opencode-config-template --skill opencode-v2-migration-skillgit clone --depth 1 https://github.com/darellchua2/opencode-config-templateWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/darellchua2/opencode-config-template/opencode-v2-migration-skill)<a href="https://agentmods.dev/skills/darellchua2/opencode-config-template/opencode-v2-migration-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/opencode-v2-migration-skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/darellchua2/opencode-config-template/opencode-v2-migration-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/opencode-v2-migration-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00091 | $0.01883 |
| Opus 5.5 | $0.00036 | $0.00753 |
| Sonnet 5.5 | $0.00018 | $0.00377 |
| Haiku 4.5 | $0.00009 | $0.00188 |
Grade A, and why
opencode-v2-migration-skill scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 28d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| Scripts/integrations calling the V1 server API (curl, SDK) | scripts, CI, apps | v2 HTTP API (`/api/*`, breaking) — port to `opencode api`, `@opencode/client`, or the new endpoints; see the [API reference](https://open How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenCode v1 → v2 Migration
Frontend for migrating an end user's OpenCode v1 setup to v2: detect what is
V1, decide the migration scope, then delegate execution to
opencode-v2-migration-subagent (which carries the full field-mapping tables).
Source of truth: https://opencode.ai/v2/docs/migrate-v1/ — re-fetch
before acting; v2 is evolving. Never use opencode.ai/docs/... (V1 docs).
Phase 1 — Detection
Version + migration-state probes (v2 HTTP API)
opencode --version # v1.x = V1 client; v2.x = V2
opencode service status # v2-only command; failing ⇒ no v2 service
opencode api get /api/status # v2 server status (v1 clients lack `api`)
opencode api get /api/experimental/migration/v1 # v2's built-in V1-migration status report
/api/experimental/migration/v1 is the authoritative in-product probe — it
reports what the v2 server still detects as V1-shaped. Full API surface:
https://opencode.ai/v2/docs/api/ (OpenAPI at /openapi.json on any running
server); TypeScript client: @opencode/client.
V1 artifact signals
Check each; every hit is a migration item:
| Signal | Where | v2 destination |
|---|---|---|
tui.json(c) |
~/.config/opencode/, project |
~/.config/opencode/cli.json (auto-migrated on first v2 TUI start; verify) |
permission map, legacy top-level tools (deprecated) |
any config JSON | ordered permissions array (bash→shell, task→subagent, write/patch→edit) |
agent / provider / command / plugin / reference (singular) |
config JSON | agents / providers / commands / plugins / references |
prompt, disable, variant, top-level temperature |
agent entries + .md frontmatter |
system, disabled, model#variant, request.body.temperature (auto-translated — optional) |
mcp direct server map, enabled |
config JSON | mcp.servers + inverse disabled. Two stub traps: (1) V1 enable-only stubs ({"<name>": {"enabled": true}}, no type) are silently omitted by v2; (2) project-level "enable the global one" overrides must be full entries — v2 replaces mcp.servers.<name> atomically, so a bare {"disabled": false} stub yields an inert server. Copy the transport (type/command/env) from the global entry and set disabled: false |
V1 TUI plugin in cli.json (tui: async-function export) |
~/.config/opencode/cli.json |
v2 CLI plugins need Plugin.define({id, setup}) via @opencode/plugin/tui (or a ./tui package export) — see the CLI plugin guide. Remove V1-only entries (watch-list) until upstream ports |
agent/, mode/, command/, skill/, plugin/ dirs |
.opencode/ |
agents/, agents/ + mode: primary, commands/, skills/, plugins/ (old dirs still discovered) |
| V1 plugin code | plugins array entries |
does not run on v2 — port per the plugin migration guide or drop |
autoupdate, small_model, enabled_providers |
config JSON | update, agents.title.model, internal policies (normalized silently) |
lsp config expecting diagnostics |
config JSON | v2 accepts but never runs language servers — use lint/typecheck commands |
instructions field |
config JSON | accepted but not loaded — move content to AGENTS.md |
Global config named config.json |
~/.config/opencode/ |
rename to opencode.json — v2 only reads opencode.json(c) |
/global/health healthchecks |
scripts, compose files | /api/health |
| Scripts/integrations calling the V1 server API (curl, SDK) | scripts, CI, apps | v2 HTTP API (/api/*, breaking) — port to opencode api, @opencode/client, or the new endpoints; see the API reference |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 28d ago Changed · +1 lines 32e11d52a5fc
- 1mo ago First seen · 117 lines · 91 tokens per session scan A 465a725ac90d
opencode-v2-migration-skill is a skill published in the GitHub repository darellchua2/opencode-config-template (6 stars, last pushed 28d ago), licensed Apache-2.0. It adds 91 tokens to every session and 1,883 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-15.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…