bw-mcp: Skill for Claude Code

.agents/skills/bw-proxy/SKILL.md

bw-proxy is a skill for Claude Code, Codex from KpihX/bw-mcp. It costs 21 tokens per session (819 once invoked), scanned A, original, MIT.

A command-line skill for managing Bitwarden vault items through a proxy while keeping secret values hidden from the AI agent. Bitwarden is a password and sensitive-information manager.

In plain words
What is it for?
Use it to inspect a redacted vault structure, manage vault items, check the connection, and lock or unlock short-lived sessions.
Why use it?
It supports vault administration and audits without revealing passwords or other secret contents to the agent.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is KpihX/bw-mcp's own configuration. It tells Claude Code and Codex how to work on bw-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything bw-mcp configures →

View source ↗ KpihX/bw-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to KpihX/bw-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/KpihX/bw-mcp/master/.agents/skills/bw-proxy/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/KpihX/bw-mcp

Made for: Claude Code, 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 bw-proxy

README.md
[![agentmods](https://agentmods.dev/badge/skills/kpihx/bw-mcp/bw-proxy.svg)](https://agentmods.dev/skills/kpihx/bw-mcp/bw-proxy)
Your own site
<a href="https://agentmods.dev/skills/kpihx/bw-mcp/bw-proxy"><img src="https://agentmods.dev/badge/skills/kpihx/bw-mcp/bw-proxy.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 819 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 $0.00021 $0.00819
Opus 5 $0.00010 $0.00409
Sonnet 5 $0.00004 $0.00164
Haiku 4.5 $0.00002 $0.00082

Measured 6d ago against content hash d74f095815d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

bw-proxy 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 6d 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.

.agents/skills/bw-proxy/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🛡️ BW-Proxy Skill

This skill allows AI agents to interact with the BW-Proxy appliance via its CLI surface. The CLI uses RPC 2.0 (JSON) and is the recommended way for both humans and AI agents to manage the vault efficiently.

🎯 Primary Goal

Manage Bitwarden vault items (Login, Note, Card, Identity) and perform blind audits/refactoring while remaining strictly blind to secret values.


🛠️ Operational Map

1. Administration (admin)

Use these commands to manage the appliance state and authentication.

Command Purpose
bw-proxy admin login Initialize vault connection (URL, Email).
bw-proxy admin status Check connection health and lock state.
bw-proxy admin unlock Create a short-lived (5m) encrypted session lease.
bw-proxy admin lock Immediately wipe the session lease and lock the proxy.
bw-proxy admin config edit Open the secure browser-based YAML editor.

2. Vault Operations (do)

These are the core tools for AI agents. Most commands support --format json (default for many) and --rationale.

🔍 Discovery
  • get-vault-map: Fetch the redacted structure of the vault.
    • Usage: bw-proxy do get-vault-map [--folder-id ID] [--collection-id ID]
  • list-items: Fast redacted item listing.
    • Usage: bw-proxy do list-items [--search STRING] [--n 50]
  • inspect-log: View previous transactions and their outcomes.
    • Usage: bw-proxy do inspect-log [-n 10]
🏗️ Transactions (ACID)
  • propose-vault-transaction: Simulate and log a batch of edits/creations.
    • Usage: bw-proxy do propose-vault-transaction --rationale "..." --operations-json '[...]'
  • execute-vault-transaction: Commit a previously proposed transaction to the real vault.
    • Usage: bw-proxy do execute-vault-transaction --tx-id ID
🧹 Audit & Refactor
  • find-item-duplicates: Scan vault for items sharing the same secret as a target.
    • Usage: bw-proxy do find-item-duplicates --item-id ID --field login.password
  • vault-refactor: Move or copy secrets between items (Blindly).
    • Usage: bw-proxy do vault-refactor --operation MOVE --source-id ID --dest-id ID

Read the full file on GitHub · 69 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. 6d ago First seen · 69 lines · 21 tokens per session scan A d74f095815d1

Subscribe to this mod's changes

bw-proxy is a skill published in the GitHub repository KpihX/bw-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 819 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens