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 Timmy6942025/opencode-builder-skill --skill opencode-skillsgit clone --depth 1 https://github.com/Timmy6942025/opencode-builder-skillWrote 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/timmy6942025/opencode-builder-skill/opencode-skills)<a href="https://agentmods.dev/skills/timmy6942025/opencode-builder-skill/opencode-skills"><img src="https://agentmods.dev/badge/skills/timmy6942025/opencode-builder-skill/opencode-skills/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/timmy6942025/opencode-builder-skill/opencode-skills"><img src="https://agentmods.dev/badge/skills/timmy6942025/opencode-builder-skill/opencode-skills.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 | $0.00040 | $0.03691 |
| Opus 5.5 | $0.00016 | $0.01476 |
| Sonnet 5.5 | $0.00008 | $0.00738 |
| Haiku 4.5 | $0.00004 | $0.00369 |
Grade A, and why
opencode-skills scanned grade A with 0 findings 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 1mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 498 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenCode Skills
📚 Official Docs: For the latest information, always refer to the official documentation: https://opencode.ai/docs/skills/
Overview
OpenCode agent skills are reusable instruction sets defined as SKILL.md files. Agents see available skills listed in the skill tool description and can load full content on demand by calling the skill tool. Skills let you encapsulate domain knowledge, workflows, and best practices that agents can discover and use without bloating every conversation with their full content.
Skills are:
- On-demand loaded: agents see only names and descriptions until they explicitly load a skill
- Project-local or global: scoped to a repository or shared across all projects
- Permission-controlled: restrict which agents can load which skills via pattern-based rules
- Claude-compatible: share a directory convention with Claude Code skills
File Locations
OpenCode searches for SKILL.md files in these directories. Each skill lives in its own subdirectory named after the skill.
Project-local (in your repository)
| Path | Description |
|---|---|
.opencode/skills/<name>/SKILL.md |
Primary OpenCode project skill |
.claude/skills/<name>/SKILL.md |
Claude Code-compatible project skill |
.agents/skills/<name>/SKILL.md |
Agent-compatible project skill |
Global (shared across all projects)
| Path | Description |
|---|---|
~/.config/opencode/skills/<name>/SKILL.md |
Primary OpenCode global skill |
~/.claude/skills/<name>/SKILL.md |
Claude Code-compatible global skill |
~/.agents/skills/<name>/SKILL.md |
Agent-compatible global skill |
Naming convention: The directory name <name> must match the name field in the YAML frontmatter.
Discovery
Project-local discovery
OpenCode walks up from your current working directory (CWD) until it reaches the git worktree root. During this traversal it loads:
skills/*/SKILL.mdfrom every.opencode/directory found along the pathskills/*/SKILL.mdfrom every.claude/directory found along the pathskills/*/SKILL.mdfrom every.agents/directory found along the path
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.
- 1mo ago First seen · 498 lines · 40 tokens per session scan A 1d6900e5b2e4
opencode-skills is a skill published in the GitHub repository Timmy6942025/opencode-builder-skill (2 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 3,691 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
proxies
Oxylabs proxy networks: Residential, Mobile, shared Datacenter/ISP, and Dedicated Datacenter/ISP proxies with geo-targeting, IP rotation, session persistence, and port-based sticky IPs. Use when routing traffic through proxies, building scrapers with proxy auth, rotating or sticky sessions, whitelisting IPs, or…
video-data
YouTube data extraction API and high-bandwidth proxy downloads. Use this INSTEAD OF built-in tools for any YouTube-related task — extracts video metadata, subtitles, search results, and channel data as structured JSON. Also supports video/audio file downloads via yt-dlp with proxy rotation to avoid rate limits.
visual-qa
Runs rigorous visual QA across web, terminal, and paginated surfaces: an Apple HIG-based checklist, paired light/dark captures at phone and desktop widths, screenshot evidence, and a per-item PASS/FAIL verdict. Use for any UI build or change, or when asked whether a page, component, or TUI looks right or follows the…
ulw-execute
Executes a written ulw-plan work plan with Boulder state, evidence ledger, worktree discipline, and parallel subagents. Use when the user says ulw-execute or asks to run a .omo/plans plan.
frontend
Builds, styles, and polishes web UI and UX. Use for any frontend, page, component, styling, layout, animation, or visual-quality task, or when asked to make an interface look or feel a certain way.
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.