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/vellum-skills/e2e/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/e2e)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/e2e"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/e2e/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/e2e"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/e2e.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 | $0.00014 | $0.00638 |
| Opus 5 | $0.00007 | $0.00319 |
| Sonnet 5 | $0.00003 | $0.00128 |
| Haiku 4.5 | $0.00001 | $0.00064 |
Grade A, and why
e2e 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run end-to-end tests via the CI workflow.
The user may pass $ARGUMENTS to filter to a specific test case by name (e.g., hello-world, phone-setup). If not provided, infer options from context (see below).
Steps
1. Determine options
Experimental tests: Always include --experimental by default. The user can pass --no-experimental to exclude them.
Branch detection: Check what branch you're on via git branch --show-current. If you're on a branch other than main, automatically pass -b <branch-name> so the CI run tests against that branch. The user can override with -b <other-branch> explicitly.
Test case filter: Determine which test case to target:
- If the user passes a bare word argument (e.g.,
phone-setup), use that as the filter. - Otherwise, look at the conversational context - if you've been working on or discussing a specific e2e test case (e.g., editing
playwright/cases/phone-setup.md), automatically target that test case. - If neither applies, run all tests.
Additional flags from $ARGUMENTS:
--xcodeuses the agent-xcode (AXUIElement) runner-dor--detachtriggers the run and exits without polling--no-experimentaloverrides the default and excludes experimental tests
2. Trigger the CI run
cd playwright && bun run scripts/agent-ci.ts <options>
Map the resolved options:
- Test case filter:
-t <case-name> - Experimental (default on):
--experimental - Branch:
-b <branch-name> - Xcode runner:
--xcode - Detach mode:
-d
Examples:
/e2e(on main, no context) →bun run scripts/agent-ci.ts --experimental/e2e(on branchfeat/phone, after editingphone-setup.md) →bun run scripts/agent-ci.ts --experimental -b feat/phone -t phone-setup/e2e hello-world(on main) →bun run scripts/agent-ci.ts --experimental -t hello-world/e2e --detach(on branchfix/bug) →bun run scripts/agent-ci.ts --experimental -b fix/bug -d/e2e --no-experimental→bun run scripts/agent-ci.ts
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 · 57 lines · 14 tokens per session scan A 019129eff285
e2e is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,214 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 638 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
ci-all
Full CI pipeline: run local tests, type check, push branch, and return the pipeline URL. The only command you need before opening a PR.
chaos-experiment
Design and document chaos engineering experiments. Guide steady state baseline, hypothesis formation, failure injection plans, and results analysis. Use when you say "design a chaos experiment", "plan a game day", "failure injection", "test resilience", or "chaos engineering". Do NOT use for security threat analysis…
api-integration-test
Create, maintain, and run gated Go integration tests for internal APIs and service-to-service clients (HTTP/gRPC). Use for endpoint verification, contract checks with real runtime config, opt-in execution, timeout/retry safety, and integration failure triage in Go services.
e2e-test
Design, maintain, and execute reliable end-to-end tests for critical user journeys with Agent Browser as first choice for exploration and Playwright as the preferred code path for suites and CI. Use for E2E strategy, journey coverage, flaky test triage, artifact collection, CI gating, regression prevention, and…
self-testing
E2E self-testing workflow for vibing.nvim using a separate Neovim instance controlled over RPC. Use when writing or debugging E2E tests, running npm run test:e2e, or executing the 3-try auto-fix rule after implementing a feature. Covers the…
test-design
Automatically design comprehensive E2E test cases for newly implemented vibing.nvim features. Use immediately after completing feature implementation (Phase 5.4) and before running E2E tests. Generates test scenarios covering Happy paths, Error cases, Edge cases, and Integration points with priority ranking…