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/.cursor/skills/vellum-test-selection/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/vellum-test-selection)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/vellum-test-selection"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/vellum-test-selection/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/vellum-test-selection"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/vellum-test-selection.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 | $0.00045 | $0.00493 |
| Opus 5 | $0.00023 | $0.00246 |
| Sonnet 5 | $0.00009 | $0.00099 |
| Haiku 4.5 | $0.00005 | $0.00049 |
Grade A, and why
vellum-test-selection scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vellum Test Selection
Core Rule
Never run unscoped bun test in this repository. The full suite is large and can hang or time out. Choose focused tests based on changed files, then add typechecking when the change affects shared contracts or cross-package behavior.
Setup
Before any Bun command:
export PATH="$HOME/.bun/bin:$PATH"
Run commands from the package directory that owns the changed files, usually assistant, gateway, cli, clients/web, or clients/macos.
Selection Workflow
- List changed files and group them by package.
- For direct implementation/test pairs, run the matching test file.
- For route, protocol, migration, IPC, provider, or schema changes, run nearby tests plus a package typecheck.
- For shared TypeScript contracts, run tests for each consumer package that imports the contract.
- For Swift or macOS client changes, prefer the existing platform-specific test command if one is already used in nearby docs or terminal history.
- If a command is expected to be long-running, state that before running it.
Common Commands
Assistant focused test:
cd assistant && bun test src/path/to/file.test.ts
Assistant test grep:
cd assistant && bun test src/path/to/file.test.ts --grep "case name"
Assistant typecheck:
cd assistant && bunx tsc --noEmit
Gateway focused test:
cd gateway && bun test src/path/to/file.test.ts
Risk-Based Additions
Add typecheck when edits touch:
- exported TypeScript types or schemas
- route request/response shapes
- daemon/client protocols
- migrations and registry wiring
- package boundary imports
- provider abstractions
- feature flag registry or resolver code
Add migration tests when edits touch:
assistant/src/persistence/migrations/assistant/src/workspace/migrations/- persisted workspace files
- database schema modules
Reporting
When proposing or running verification, explain why each command is selected and note anything intentionally skipped.
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.
- 12d ago First seen · 79 lines · 45 tokens per session scan A 81ea7c76d873
vellum-test-selection is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,234 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 493 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.
Other skills, from other repositories
verification-engine
Use when verifying build/test/lint before commit, PR, or completion claims. Runs verification pipeline in fresh subagent context with auto-repair. Triggers on /handoff-verify, pre-commit check, build verification, test validation.
verify-implementation
A workflow that runs a project’s verification skills to produce a report on coding patterns, architecture rules, and project conventions. It is intended for work after implementation, before a pull request, or during code review.
ha-test-strategy
Hope-native test strategy for features, fixes, and refactors: select test-first, regression-first, characterization, integration, E2E, or manual evidence according to risk and repository rules.
ha-verify
Hope-native completion and verification discipline: map each requirement to current direct evidence, choose the smallest sufficient checks, and distinguish proven, failed, blocked, stale, or unverified claims.
voice-agent-test-harness
Drive a fixed suite of spoken tests against a voice agent ("subject") from a co-located machine ("prober"), measure response latency / clarity / accuracy, diff against baseline, and report to the owner over Telegram.
playbook-webapp
Web application pentest methodology + ROUTER to the per-vuln-class web skills. Load at the START of systematic web testing to get the phase flow (recon → map → test-by-OWASP-class → prove → report) and pick which web- skill to load for each surface. Use on any web app / HTTP API engagement.