Playbooks

What the source does

• FilesystemUndeclared5 observations, not in its own description
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

assistant/CLAUDE.md

assistant/src/approvals/CLAUDE.md

assistant/src/notifications/CLAUDE.md

assistant/src/runtime/CLAUDE.md

gateway/CLAUDE.md

import { getMemoryDb } from "../../../../persistence/db-connection.js";

} from "../../../../persistence/jobs-store.js";

import { memoryGraphNodes } from "../../../../persistence/schema/index.js";

} from "../../../../playbooks/types.js";

} from "../../../../plugins/defaults/memory/graph/store.js";

Audit 0.4.1 · source sha 19bc86343b63 · 14 Oct 2026Report an issue or request a re-scan

• Publishervellum-ai GitHub organizationOwner of the repository this skill is read from
• Source foldervellum-ai/vellum-assistant/assistant/src/config/bundled-skills/playbooksThe exact folder we audited
• LicenceMITAs the repository states it
• Commit pinned for this verdict19bc86343b63A new audit runs when the source changes
• Repository statusNot archivedLast push 1 day ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Trigger-action automation rules for handling incoming messages

---
name: playbooks
description: Trigger-action automation rules for handling incoming messages
compatibility: "Designed for Vellum personal assistants"
metadata:
  emoji: "📖"
  vellum:
    display-name: "Playbooks"
    category: "productivity"
---

Playbooks are trigger-action automation rules that tell the assistant how to handle incoming messages matching a pattern.

## Structure

Each playbook has:

- **Trigger**: Pattern or description that activates the rule (e.g. "meeting request", "from:ceo@*")
- **Action**: What to do when triggered (natural language description)
- **Channel**: Which channel the rule applies to ("*" = all channels, or specific like "email", "slack")
- **Category**: Free-form grouping label (e.g. "scheduling", "triage")
- **Autonomy level**: How much autonomy the assistant has
  - `auto` -- execute immediately without asking
  - `draft` -- prepare a response for user review (default)
  - `notify` -- alert the user only
- **Priority**: Numeric priority for overlapping rules (higher = takes precedence)

## Lifecycle

1. Create a playbook with `playbook_create` specifying trigger and action.
2. List existing playbooks with `playbook_list`, optionally filtering by channel or category.
3. Update rules with `playbook_update` or remove them with `playbook_delete`.

## Storage

Playbooks are stored as memory items with semantic retrieval, enabling fuzzy matching of incoming messages against trigger patterns.

Excerpt, first 1,449 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/vellum-ai/vellum-assistant
git -C vellum-assistant checkout 19bc86343b63

Works in

1. 2026-10-14
   ✓SAFE B 89 / 100

   first audit · source 19bc86343b63

Questions about Playbooks

• github.com/vellum-ai/vellum-assistant/tree/main/assistant/src/co — the audited source at commit 19bc86343b63 and every finding aboveObserved · 14 Oct 2026

Spotted something wrong? Report a correction · Methodology