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-change-review/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-change-review)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/vellum-change-review"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/vellum-change-review/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-change-review"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/vellum-change-review.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 | $0.00063 | $0.00540 |
| Opus 5 | $0.00032 | $0.00270 |
| Sonnet 5 | $0.00013 | $0.00108 |
| Haiku 4.5 | $0.00006 | $0.00054 |
Grade A, and why
vellum-change-review 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 13d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vellum Change Review
Review Stance
Prioritize bugs, behavioral regressions, security risks, migration gaps, broken package boundaries, and missing tests. Findings come before summaries. Avoid cosmetic feedback unless it affects correctness, maintainability, or user experience.
Required Checks
- Inspect the actual diff before judging the change.
- Identify which packages are affected:
assistant,gateway,clients,cli,skills,packages, ormeta. - Check package boundaries:
assistantmust not import fromgatewayby relative path.gatewaymust not import fromassistantby relative path.assistantandskillsmust not import each other directly.- Runtime code must not import from
meta.
- Check persistence changes:
- DB schema or data changes need append-only DB migrations.
- Workspace path, format, or file changes need append-only workspace migrations.
- Migrations must be idempotent and registered.
- Check feature flags:
- New assistant flags must be declared in
meta/feature-flags/feature-flag-registry.json. - Default-disabled or rollout-only features must not ship user-facing release notes.
- New flags may require a companion platform PR.
- New assistant flags must be declared in
- Check user-facing text:
- User-facing copy should say "assistant", not "daemon".
- Examples must use generic names, emails, phone numbers, and IDs.
- Check LLM/provider usage:
- LLM calls must go through the provider abstraction.
- Comments and logs should use provider-agnostic wording.
- Check tests and verification:
- Look for focused tests covering changed behavior.
- Prefer scoped
bun test path/to/test.ts; never suggest broadbun test. - Suggest
bunx tsc --noEmitwhen type-level risk is broad.
Review Output
Use this structure:
## Findings
- [severity] `path`: issue, impact, and concrete fix.
## Open Questions
- Any uncertainty that affects correctness or review confidence.
## Verification Gaps
- Tests or checks that still need to run.
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.
- 13d ago First seen · 56 lines · 63 tokens per session scan A 633c8aa0d141
vellum-change-review is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,234 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 540 once invoked, about $0.0003 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
bootstrap-repo-analysis
First-time analysis of a repository with no prior reviewer outcomes. Crawl historical merged-PR review feedback with the gh CLI (plus any preloaded samples), extract the team's review norms, and synthesize the initial per-repo review-style prompt. Use this for a cold-start repo; use continual-learning instead once the…
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…
oracle
Oracle second-model review: bundle prompts/files, debug, refactor, design.
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.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
frontend-code-review
Trigger when the user requests a review of frontend files (e.g., .tsx, .ts, .js). Support both pending-change reviews and focused file reviews while applying the checklist rules.