vellum-assistant: Skill for Claude Code

.claude/skills/update/SKILL.md

update is a skill for Claude Code from vellum-ai/vellum-assistant. It costs 49 tokens per session (1,136 once invoked), scanned A, original, MIT.

A restart command for the Vellum assistant and gateway services, with options for updating or switching Git branches.

In plain words
What is it for?
Restarting Vellum on the current branch, updating from the main branch, switching to another branch, or forcing a pull.
Why use it?
It avoids manually stopping services, choosing the right branch, and pulling changes before a restart.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is vellum-ai/vellum-assistant's own configuration. It tells Claude Code how to work on vellum-assistant 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 vellum-assistant configures →

About the project

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.

vellum-ai/vellum-assistant · 1,214 stars · on GitHub · vellum.ai

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/vellum-ai/vellum-assistant/main/.claude/skills/update/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vellum-ai/vellum-assistant

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 update

README.md
[![agentmods](https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/update/github.svg)](https://agentmods.dev/skills/vellum-ai/vellum-assistant/update)
Your own site
<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/update"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/update/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 update

Your own site · 80×15
<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/update"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,136 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00049 $0.01136
Opus 5 $0.00024 $0.00568
Sonnet 5 $0.00010 $0.00227
Haiku 4.5 $0.00005 $0.00114

Measured 10d ago against content hash 35604b556c32, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

update 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 10d 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/update/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update - Restart Vellum (with Smart Branch Handling)

Restart the Vellum assistant and gateway services with branch-aware git behavior.

Arguments

The user may pass $ARGUMENTS to control branch behavior:

Invocation Behavior
/update (no args, on main) Pull latest from origin/main (default)
/update (no args, on a feature branch) Skip git ops - restart with the current checkout
/update <branch> Check out that branch, pull if it has a remote
/update --pull Force pull on whatever branch you're currently on

Steps

  1. Ensure Bun is on PATH:

    export PATH="$HOME/.bun/bin:$PATH"
    
  2. Preflight snapshot - capture current state before making changes:

    vellum ps
    
  3. Quiesce with vellum sleep - stop assistant and gateway processes. This is directory-agnostic and stops processes globally regardless of CWD:

    vellum sleep || true
    
  4. Verify stopped - run vellum ps and confirm no running processes. If vellum ps shows processes still running, run fallback cleanup to force-kill them:

    vellum ps
    

    Fallback cleanup if vellum ps confirms processes are still running:

    pkill -x "vellum-assistant" || true
    pkill -f "gateway/src/index" || true
    lsof -ti :7830 | xargs kill -9 2>/dev/null || true
    lsof -ti :7821 | xargs kill -9 2>/dev/null || true
    

    After fallback cleanup, run vellum ps again to confirm all processes are stopped.

  5. Smart branch handling - determine what git operations (if any) to perform:

    CURRENT=$(git branch --show-current)
    GIT_OPS_RAN=false
    

    Case A - --pull flag: Force pull on the current branch.

    if [[ "$ARGUMENTS" == "--pull" ]]; then
      git pull
      GIT_OPS_RAN=true
    fi
    

    Case B - Explicit branch name provided: Check out the requested branch, pulling if possible. Before checking out, verify the working tree is clean - if there are uncommitted changes, stop and warn the user rather than silently losing work. Do NOT stash automatically.

    if [[ -n "$ARGUMENTS" && "$ARGUMENTS" != "--pull" ]]; then
      if ! git diff --quiet || ! git diff --cached --quiet; then
        echo "ERROR: Uncommitted changes detected. Commit or stash them before switching branches."
        # Stop and report the error to the user. Do not proceed.
      fi
      git checkout "$ARGUMENTS"
      git pull origin "$ARGUMENTS" 2>/dev/null || true
      GIT_OPS_RAN=true
    fi
    

Read the full file on GitHub · 125 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. 10d ago First seen · 125 lines · 49 tokens per session scan A 35604b556c32

Subscribe to this mod's changes

update is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,214 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 1,136 once invoked, about $0.0002 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

baby-sit

Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.

langchain-ai/open-swe · 30 tokens

security-pipeline

Use when security verification is needed - pre-commit security checks, vulnerability scanning, STRIDE threat analysis. Integrates with /handoff-verify --security and /commit-push-pr. CWE Top 25 based.

sangrokjung/claude-forge · 48 tokens

engine-conflict-resolve

Ask Sutando to resolve a conflicted update of a Sutando checkout. When pulling the latest release/main conflicts with local changes, Sutando reproduces the merge in a scratch git worktree, resolves the conflicts there, proposes the resolution to the owner, and fast-forwards the live checkout only after explicit…

sonichi/sutando · 87 tokens

submit-use-case

OSS-facing channel to share a Sutando use case with the community. Opens a labeled GitHub issue on sonichi/sutando and (CLA-gated) a PR adding docs/community-use-cases/ .md. Validates outcome-framed titles with the same checker as add-use-case. Default: both; flags --issue-only / --pr-only opt out.

sonichi/sutando · 79 tokens

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…

sonichi/sutando · 68 tokens

review-preflight

Review tooling for a PR: review-preflight prints REVIEW.md's criteria and the PR's live gate state before a review; ci-triage maps a PR's failing checks to already-filed issues.

sonichi/sutando · 45 tokens