How do I install the Bitwarden Secrets skill?

Run npx skillmds@latest add modbender/bitwarden-secrets in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Bitwarden Secrets safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: executes scripts, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Bitwarden Secrets?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Bitwarden Secrets free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Bitwarden Secrets?

modbender (@modbender) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Bitwarden Secrets by modbender — Agent Skill

Name: Bitwarden Secrets
Rating: 4.2 (5 reviews)
Author: modbender

Bitwarden Secrets

Safely access Bitwarden or Vaultwarden secrets via the bw CLI with redacted outputs by default. Use for vault sync, item search, metadata retrieval, and (only with explicit confirmation) revealing a single secret field.

modbender Updated Sep 9, 2026 12 repo stars

File contents

Bitwarden Secrets (safe-by-default)

Use this skill to interact with Bitwarden/Vaultwarden through bw while minimizing accidental secret leakage.

Prerequisites

bw CLI installed.
Server configured (bw config server <url>).
Logged in (bw login --apikey) and unlocked (bw unlock) so BW_SESSION is available.

Commands

cd skills/bitwarden-secrets
python3 scripts/vw_cli.py status
python3 scripts/vw_cli.py sync
python3 scripts/vw_cli.py search --query google
python3 scripts/vw_cli.py get --id <item_id>

Bootstrap helper (optional)

Load runtime vars + refresh session + sync in one step:

source scripts/vw_bootstrap.sh
# or after shell reload:
vw-openclaw-ready

Reveal (explicit only)

By default, do not reveal secret values in chat. Use reveal only with explicit user consent and temporary policy override:

export VW_REVEAL_ALLOW=1
python3 scripts/vw_cli.py reveal --id <item_id> --field password --confirm YES_REVEAL
unset VW_REVEAL_ALLOW

Safety policy

Default outputs are redacted/metadata-only.
No bulk secret dumps.
Prefer IDs + labels and retrieve only the minimum needed field.
Reveal requires BOTH VW_REVEAL_ALLOW=1 and --confirm YES_REVEAL.

Frequently asked questions