meridian: Skill for Claude Code

.claude/skills/release/SKILL.md

release is a skill for Claude Code from Meridiona/meridian. It costs 29 tokens per session (1,755 once invoked), scanned A, original, MIT.

A release process for the Meridian monorepo, meaning one repository that contains several related software components.

In plain words
What is it for?
Releasing Meridian’s Rust daemon, user interface, MCP server, and tray app, including production and staging releases.
Why use it?
It coordinates version changes, building, signing, notarising, and publishing so the components are released together through automated workflows.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is Meridiona/meridian's own configuration. It tells Claude Code how to work on meridian 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 meridian configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is cd packages/meridian-mcp && npm run build && cd ../...

Reuse

Borrowing it

Nothing to install: this file belongs to Meridiona/meridian. 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/Meridiona/meridian/main/.claude/skills/release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Meridiona/meridian

Made for: Claude Code.

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/meridiona/meridian/release.svg)](https://agentmods.dev/skills/meridiona/meridian/release)
Your own site
<a href="https://agentmods.dev/skills/meridiona/meridian/release"><img src="https://agentmods.dev/badge/skills/meridiona/meridian/release.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,755 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 $0.00029 $0.01755
Opus 5 $0.00015 $0.00877
Sonnet 5 $0.00006 $0.00351
Haiku 4.5 $0.00003 $0.00176

Measured 7d ago against content hash 46c0556347f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 7d 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.

.claude/skills/release/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meridian Release Skill

Meridian uses semantic-release (not release-please) driven by two GitHub Actions workflows: .github/workflows/release.yml (production, on push to main) and .github/workflows/release-staging.yml (staging, on push to pre-main gated by a [staging-release] commit-message marker, or manual dispatch).

Components & Version Files

Bumped in lockstep by scripts/set-version.sh <version>:

Component Version File
Rust daemon Cargo.toml (version = "X.Y.Z"), Cargo.lock
UI ui/package.json
MCP server packages/meridian-mcp/package.json
Tray app tray/src-tauri/tauri.conf.json

Release Workflow

Production (main)

Config: .releaserc.json. Commit-message convention (conventionalcommits preset): feat: → minor, fix: → patch, feat!:/BREAKING CHANGE: → major, chore:/docs:/refactor: → no bump but included in changelog.

prepareCmd runs, in order:

  1. scripts/set-version.sh <ver> — bump all version files
  2. cargo build --release
  3. UI build (ui/), tray build (tray/, tauri build)
  4. scripts/notarize-dmg.sh <ver> — notarize + staple the .dmg (Tauri only signs+notarizes+staples the .app, not the .dmg)
  5. scripts/package-updater.sh <ver> — build latest.json from the real minisign .sig, copy the versioned DMG to a stable Meridian.dmg name
  6. scripts/verify-release-bundle.sh <ver> — hard gate: codesign identity, Gatekeeper offline acceptance, staple presence, and that the updater artifacts (.app.tar.gz, .sig, latest.json) exist and are non-empty (Tauri can silently exit 0 with a bad/missing signing key)

Then @semantic-release/github publishes Meridian.dmg, Meridian.app.tar.gz, .sig, and latest.json onto a versioned v<version> GitHub Release (becomes GitHub's "latest"), and @semantic-release/git commits the version bump + CHANGELOG.md back to main (chore(release): X.Y.Z [skip ci]).

Staging (pre-main)

Config: .releaserc.staging.json (copied over .releaserc.json at CI runtime — never the committed file). The tray builds with the tray/src-tauri/tauri.staging.conf.json overlay (different updater endpoint) and cuts a prerelease version X.Y.Z-staging.N. No version-bump commit back to pre-main. publishCmd runs scripts/mirror-staging-release.sh <ver>, which mirrors latest.json (and the DMG) onto a fixed, rolling updater-staging GitHub prerelease tag so it never leaks into production's "latest" pointer.

Read the full file on GitHub · 168 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. 7d ago First seen · 168 lines · 29 tokens per session scan A 46c0556347f2

Subscribe to this mod's changes

release is a skill published in the GitHub repository Meridiona/meridian (294 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 1,755 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

repo-guidance

Navigate the Composio SDK monorepo, branch and PR workflow, repo layout, generated-file boundaries, changesets, and shared maintenance rules. Use when work spans multiple packages, when deciding where code belongs, when preparing a PR, or when the user asks about repository conventions rather than a specific SDK…

ComposioHQ/composio · 67 tokens

python-release

Handle Python SDK release, build, bump, packaging metadata, PyPI client pin, uv.lock, nox/build workflow, and publish verification changes. Use for Python release process work or dependency pin bumps; do not use for ordinary Python feature implementation.

ComposioHQ/composio · 53 tokens

contributor

End-to-end open source contribution workflow: from scanning issues to submitting PRs. Use this skill whenever the user wants to contribute to an open source project, find issues to fix, submit a pull request, fork a repo to contribute, fix a GitHub issue, or mentions 'open source contribution'. Also trigger when they…

majiayu000/spellbook · 111 tokens

git-commit-smart

Generates meaningful, conventional commit messages automatically. Use when committing code changes. Analyzes diff to create descriptive commits following best practices.

majiayu000/spellbook · 32 tokens

push-all

Use when the user explicitly asks to stage all current changes, create a commit, and push to the remote after safety checks.

majiayu000/spellbook · 28 tokens

review-gate

Use before an agent-produced diff is committed, pushed, opened as a PR, merged, landed, or applied to user files when explicit implementation approval is missing. Trigger for review gate, review pack, approve before landing, diff first then land, human approval, merge gate, commit gate, push gate, or PR readiness.…

majiayu000/spellbook · 95 tokens