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.
curl -O https://raw.githubusercontent.com/Meridiona/meridian/main/.claude/skills/release/SKILL.mdgit clone --depth 1 https://github.com/Meridiona/meridianWrote 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/meridiona/meridian/release)<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>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 | $0.00029 | $0.01755 |
| Opus 5 | $0.00015 | $0.00877 |
| Sonnet 5 | $0.00006 | $0.00351 |
| Haiku 4.5 | $0.00003 | $0.00176 |
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.
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:
scripts/set-version.sh <ver>— bump all version filescargo build --release- UI build (
ui/), tray build (tray/,tauri build) scripts/notarize-dmg.sh <ver>— notarize + staple the.dmg(Tauri only signs+notarizes+staples the.app, not the.dmg)scripts/package-updater.sh <ver>— buildlatest.jsonfrom the real minisign.sig, copy the versioned DMG to a stableMeridian.dmgnamescripts/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.
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.
- 7d ago First seen · 168 lines · 29 tokens per session scan A 46c0556347f2
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.
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…
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.
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…
git-commit-smart
Generates meaningful, conventional commit messages automatically. Use when committing code changes. Analyzes diff to create descriptive commits following best practices.
push-all
Use when the user explicitly asks to stage all current changes, create a commit, and push to the remote after safety checks.
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.…