Vellum Assistant is a personal AI assistant that remembers information about users, learns their preferences, and takes actions across connected apps. It is intended for people who want an assistant that can manage conversations, unfinished work, and proactive notifications over time. The catalogue skills, hooks, instruction, and setting configure or extend how the assistant works.
Borrowing it
Nothing to install: this file belongs to vellum-ai/vellum-assistant. 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/vellum-ai/vellum-assistant/main/.claude/skills/release/SKILL.mdgit clone --depth 1 https://github.com/vellum-ai/vellum-assistantWrote 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/vellum-ai/vellum-assistant/release)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/release"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/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.
<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/release"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00026 | $0.00807 |
| Opus 5 | $0.00013 | $0.00404 |
| Sonnet 5 | $0.00005 | $0.00161 |
| Haiku 4.5 | $0.00003 | $0.00081 |
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 9d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cut a new release. Releases are a two-step process:
- Branch cut → staging bake:
create-release-branch.ymlcomputes the version from the bump type, deletes any stalerelease/v<X.Y.Z>branch, cuts a fresh one frommainHEAD with the version-bump commit, and pushes it. That push triggers aReleaserun on the branch which is a staging deploy (push-triggered and main-dispatchedReleaseruns are always staging). - Production: dispatching
release.ymlon therelease/v<X.Y.Z>branch runs the full production release — tag, GitHub Release, DMG sign/notarize/publish, npm packages, Docker Hub images, iOS TestFlight, platform dependency bump, and the merge-back of the release branch tomain.
The scheduled Tue/Thu 7:52am ET cut performs step 1 automatically; a human performs step 2 after the staging bake is green. A release/v<X.Y.Z> branch with no corresponding GitHub Release means a cut was never promoted. Re-running step 1 refreshes it from current main.
The user may pass $ARGUMENTS as the bump type for step 1: patch, minor, major, or hotfix (patch cut from the latest release tag's commit instead of main, pushed [skip ci] for manual cherry-picks). Default to patch.
Steps
1. Pull latest main and show the payload
git checkout main && git pull
git describe --tags --abbrev=0
git log --oneline "$(git describe --tags --abbrev=0)"..origin/main | head -20
Confirm with the user before proceeding unless they already asked for the release explicitly.
2. Cut the release branch (staging bake)
gh workflow run create-release-branch.yml \
--repo vellum-ai/vellum-assistant \
--ref main \
--field bump=<patch|minor|major|hotfix>
Then wait for the branch cut and find the staging Release run its push triggered:
gh run list --workflow="Create Release Branch" --limit 1
gh run list --workflow=Release --branch "release/v<X.Y.Z>" --limit 1
The version appears in the branch name; the staging run takes ~15-20 minutes. Wait for it to succeed — it is the CI bake for the exact release payload. If it fails, fix main and re-run this step (it recuts the branch from main HEAD).
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.
- 9d ago First seen · 74 lines · 26 tokens per session scan A 8260178a748b
release is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,214 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 807 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
release
Prepare, verify, and publish Sutando engine releases. Use when asked to prepare a release proposal, determine a version bump, audit release documentation, validate release gates, create a release PR, tag a confirmed release, or publish GitHub release notes. Preparation is safe and non-publishing; tagging and…
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.
release
Build, sign, notarize, and publish a new DroidProxy release. Use when the user wants to cut a release, merge a PR and ship it, or asks to build/notarize/publish. Covers the full pipeline: PR merge, version bump, swift build, code signing, Apple notarization, Sparkle appcast update, and GitHub release creation.
release-notes-generator
Generate release notes in 3 formats (CHANGELOG.md, PR body, Slack announcement) from git commits. Automatically categorizes changes and converts technical language to user-friendly messaging. Use for releases, changelogs, version notes, what's new summaries, or ship announcements.
release-notes
Generate release notes in multiple formats from git commits.
ship
Comprehensive pre-deployment verification to ensure release readiness.