Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Bdb Updater

ASecurity

Use when proactively checking for and installing updates to the AOS (BDB Agent OS) package via npm.

6 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgobashexpresstestingapi

Works with

cursorapi

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add hybridlabor-api/aos --skill bdb-updater --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Bdb Updater?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Bdb Updater
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hybridlabor-api-bdb-updater/badge)](https://www.skillsdirectory.com/skills/hybridlabor-api-bdb-updater)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: bdb-updater
description: Use when proactively checking for and installing updates to the AOS (BDB Agent OS) package via npm.
category: bdb-core
disable-model-invocation: true
---

# BDB Updater Skill

Keeps AOS (`@hybridlabor-api/aos`) up to date. Since v4.0.0 (renamed from
`@hybridlabor-api/bdb-dev-optimized-agent-skills`, which is deprecated on
npm and frozen at its last pre-rename version — never check that name,
it will never report a real update again).

## 1. Check for an update

```bash
npm view @hybridlabor-api/aos dist-tags --json
```

Compare against the locally installed version (`~/.agents/aos/package.json`,
or wherever the primary install target's `package.json` lives — the
installer's own `verifyEcosystemInstallation()` status table is the
authoritative source if you're running from inside an existing install).

Two dist-tags exist:
- **`@latest`** — the stable channel. CI (`release-please`) publishes here
  automatically on every release; this is what real users should run.
- **`@next`** — an ad-hoc staging tag used occasionally to validate a large
  change (a rename, a major version bump) before promotion to `@latest`.
  It is not a standing parallel channel — don't default to it unless the
  user is specifically testing a migration.

## 2. Run the update

```bash
npx -y @hybridlabor-api/aos@latest
```

`-y` runs it fully non-interactively. If an install already exists, this
takes the **Quick Update** path (refreshes skills, re-syncs installed
submodules, refreshes the OpenWiki daemon schedule) rather than a full
reinstall — it does not need a `--force` flag or any special handling for
"already installed."

The installer syncs skills to every detected harness in one pass, not
just one: `~/.claude/skills`, `~/.gemini/config/skills` (Antigravity),
`~/.agents/skills`, `~/.codex/skills`, `~/.cursor/skills`, `~/.roo/skills`.
Don't assume Gemini/Antigravity is the only target.

## 3. Verify the result

After running, `verifyEcosystemInstallation()`'s own status table (printed
at the end of the run) is the ground truth — it checks each tracked
submodule's actual installed version against its own npm dist-tags
(`bdb-synapse`, `memB`, `heimdall-token-saver`, `bdb-dev-creator-extension`,
`bdb-os-remote`, `bdb-dev-tool-installer`, and `aos` itself). Read that
table rather than assuming success from a clean exit code — a partial
failure (e.g. a daemon not responding on its port) still exits 0 and logs
a warning, not an error.

Report the new version and anything flagged as a warning in that table
(not just "update complete"). Don't report success without having actually
looked at the status table's contents.

## 4. Scheduled updates

If the user wants recurring checks, recommend `/schedule` with the current
package name:
`/schedule CronExpression="0 10 * * 1" Prompt="Check if there is a new version of @hybridlabor-api/aos via npm view and update it"`

Attribution

hybridlabor-apihybridlabor-api
View sourceMore from hybridlabor-api →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →