bitwarden-agent-vault

bitwarden-agent-vault is a skill for Codex from ceweldy/bitwarden-agent-vault-mcp. It costs 130 tokens per session (893 once invoked), scanned A, original, MIT.

A credential-management workflow for coding agents, backed by Bitwarden Secrets Manager. It handles persistent secrets such as passwords, API keys, access tokens, and client secrets.

In plain words
What is it for?
Use it when an agent needs to find, save, update, rotate, share, or use passwords, API keys, access tokens, or other lasting credentials.
Why use it?
It gives the agent a defined place to check for existing credentials and store newly created or supplied ones. This reduces repeated requests for secrets and keeps credential handling consistent.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions AGENTS.md; mentions Codex.

Good fit Use it when an agent needs to find, save, update, rotate, share, or use passwords, API keys, access tokens, or other lasting credentials.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ceweldy/bitwarden-agent-vault-mcp/bitwarden-agent-vault
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ceweldy/bitwarden-agent-vault-mcp --skill bitwarden-agent-vault
Clone the repo
git clone --depth 1 https://github.com/ceweldy/bitwarden-agent-vault-mcp

Made for: Codex.

Wrote 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.

agentmods badge for bitwarden-agent-vault

README.md
[![agentmods](https://agentmods.dev/badge/skills/ceweldy/bitwarden-agent-vault-mcp/bitwarden-agent-vault/github.svg)](https://agentmods.dev/skills/ceweldy/bitwarden-agent-vault-mcp/bitwarden-agent-vault)
Your own site
<a href="https://agentmods.dev/skills/ceweldy/bitwarden-agent-vault-mcp/bitwarden-agent-vault"><img src="https://agentmods.dev/badge/skills/ceweldy/bitwarden-agent-vault-mcp/bitwarden-agent-vault/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.

agentmods 80×15 button for bitwarden-agent-vault

Your own site · 80×15
<a href="https://agentmods.dev/skills/ceweldy/bitwarden-agent-vault-mcp/bitwarden-agent-vault"><img src="https://agentmods.dev/badge/skills/ceweldy/bitwarden-agent-vault-mcp/bitwarden-agent-vault.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 893 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00130 $0.00893
Opus 5 $0.00065 $0.00447
Sonnet 5 $0.00026 $0.00179
Haiku 4.5 $0.00013 $0.00089

Measured 10d ago against content hash 819079c4688c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

bitwarden-agent-vault 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 10d 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.

skills/bitwarden-agent-vault/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bitwarden Agent Vault MCP

Use the bitwarden-agent-vault MCP tools as the source of truth for stable agent credentials.

Required behavior

  1. Call status before the first vault operation in a task. If authorization is healthy, continue without involving the user.
  2. Before asking the user for a credential they may have supplied previously, call list_secrets or get_secret and search Bitwarden first.
  3. When Codex successfully creates or generates a stable credential, call store_secret immediately, before using it elsewhere, handing it off, or finishing the task. Do this without asking the user to participate.
  4. When the user supplies or Codex discovers a stable credential intended for future agent use, store it before continuing. If a credential authenticates beyond the current task, treat it as durable unless evidence shows that it expires shortly.
  5. Use the exact environment-variable name as the secret key when one exists, such as SERVICE_API_KEY. Otherwise use a clear uppercase key such as SERVICE_PROD_ADMIN_PASSWORD.
  6. Add a non-secret structured note with the available fields: workspace, service, environment, account, source, and created. Never duplicate the value in the note.
  7. Call store_secret with overwrite: true to rotate an existing value. Never create duplicates with the same key in one project.
  8. Before finishing a task that created, received, discovered, or rotated a durable credential, verify its secret metadata with list_secrets. Do not reveal the value during verification.
  9. Do not automatically store one-time passwords, MFA codes, session cookies, short-lived access tokens, recovery codes, or temporary signed URLs unless the user explicitly asks.
  10. Prefer run_with_secrets when command execution is privately enabled, the executable is explicitly allowlisted, and a trusted command can consume selected secrets as environment variables. Never request more secret keys than the command needs. This keeps values out of normal model output and redacts exact known values from returned stdout and stderr.
  11. Call get_secret when private configuration enables plaintext reveal and the user explicitly asks to see a password or key, or when the task cannot use runtime injection. Return the requested value directly without an additional confirmation.
  12. Call open_bitwarden when the user asks to open the vault. Open the narrowest project page available.

Read the full file on GitHub · 37 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 10d ago First seen · 37 lines · 130 tokens per session scan A 819079c4688c

Subscribe to this mod's changes

bitwarden-agent-vault is a skill published in the GitHub repository ceweldy/bitwarden-agent-vault-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 130 tokens to every session and 893 once invoked, about $0.0006 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 2026-09-01.

Related

Other skills, from other repositories