elysiajs-mcp: Skill for OpenCode

.opencode/skills/release/SKILL.md

release is a skill for OpenCode from dvaJi/elysiajs-mcp. It costs 116 tokens per session (1,795 once invoked), scanned A, original, MIT.

A set of release instructions for this package, covering version selection, changelog generation, checks, and publishing through a GitHub Release. A semantic version is a version number whose parts describe the kind of change being released.

In plain words
What is it for?
Use it when creating, cutting, publishing, or bumping a release. It helps run the required type checks, tests, build, version update, changelog update, and GitHub Release steps.
Why use it?
It defines the required checks and repository conditions before release and avoids publishing directly from a developer's computer. It also separates preparing a release from triggering the automated npm publication workflow.

Skill for OpenCode

Written for OpenCode: installed under .opencode/.

This is dvaJi/elysiajs-mcp's own configuration. It tells OpenCode how to work on elysiajs-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything elysiajs-mcp configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is - <commit subject> ([`<short hash>`](../../commit/<full hash>)).

Reuse

Borrowing it

Nothing to install: this file belongs to dvaJi/elysiajs-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dvaJi/elysiajs-mcp/main/.opencode/skills/release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dvaJi/elysiajs-mcp

Made for: OpenCode.

Wrote 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.

agentmods badge for release

README.md
[![agentmods](https://agentmods.dev/badge/skills/dvaji/elysiajs-mcp/release/github.svg)](https://agentmods.dev/skills/dvaji/elysiajs-mcp/release)
Your own site
<a href="https://agentmods.dev/skills/dvaji/elysiajs-mcp/release"><img src="https://agentmods.dev/badge/skills/dvaji/elysiajs-mcp/release/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.

agentmods 80×15 button for release

Your own site · 80×15
<a href="https://agentmods.dev/skills/dvaji/elysiajs-mcp/release"><img src="https://agentmods.dev/badge/skills/dvaji/elysiajs-mcp/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,795 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00116 $0.01795
Opus 5 $0.00058 $0.00898
Sonnet 5 $0.00023 $0.00359
Haiku 4.5 $0.00012 $0.00179

Measured 8d ago against content hash a26d0048db14, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

release 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 8d 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.

.opencode/skills/release/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release

This project releases via the Release GitHub Actions workflow (.github/workflows/release.yml), which publishes to npm with provenance when a GitHub Release is published. So "doing a release" means: prepare version + changelog locally, then create a GitHub Release — never run npm publish locally.

Pre-requisites that must already exist (if missing, stop and tell the user):

  • a git repo with a main branch and a remote called origin
  • gh CLI authenticated (gh auth status)
  • the NPM_TOKEN repo secret set in GitHub (you cannot verify this locally; just remind the user once)

Flow

Work through these steps in order. Use the bash tool for git/gh, the edit/write tools for package.json / CHANGELOG.md, and bun for local verification (typecheck / test / build).

1. Sanity-check the working copy

  • git rev-parse --abbrev-ref HEAD → expect main. If not, ask the user whether to proceed.
  • git status --porcelain → must be empty. If not, ask the user to commit or stash first; do not commit unrelated changes as part of the release.
  • bun run check && bun test && bun run build → must pass (runs oxlint, oxfmt format check, and typecheck). Stop and report if it fails.

2. Determine the previous version and the commit range

git describe --tags --abbrev=0
  • If a tag is returned, that is PREV_TAG and the range is $PREV_TAG..HEAD.
  • If the command errors (no tags yet — first release), use the whole history (git log with no range).

These examples use POSIX-shell syntax; if the local shell is PowerShell (this project's default platform is Windows), translate accordingly — e.g. redirect stderr with 2>$null instead of 2>/dev/null, and don't rely on || true (use try/catch or check $?).

3. Collect commits and infer the bump

# with a previous tag:
git log $PREV_TAG..HEAD --pretty=format:"%h%x09%s"
# first release (no prior tag):
git log --pretty=format:"%h%x09%s"

Read the full file on GitHub · 189 lines

Changes

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.

  1. 8d ago First seen · 189 lines · 116 tokens per session scan A a26d0048db14

Subscribe to this mod's changes

release is a skill published in the GitHub repository dvaJi/elysiajs-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 116 tokens to every session and 1,795 once invoked, about $0.0006 per session on Opus 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.