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.
npx agentmods add instructions/bchoor/bws-mcp/agents-mdgit clone --depth 1 https://github.com/bchoor/bws-mcpWrote 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.
[](https://agentmods.dev/instructions/bchoor/bws-mcp/agents-md)<a href="https://agentmods.dev/instructions/bchoor/bws-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/bchoor/bws-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00817 | $0.00817 |
| Opus 5 | $0.00409 | $0.00409 |
| Sonnet 5 | $0.00163 | $0.00163 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
bws-mcp AGENTS.md 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bws-mcp
Cloudflare Worker that exposes Bitwarden Secrets Manager as remote MCP. Tools: bws_list_projects, bws_list_secrets, bws_get_secret, bws_put_secret (create or update), bws_delete_secret. Secret tools require project (BWS project name). BWS_ALLOWED_PROJECTS is * (every project the machine token can see) or a comma list of names. Empty is not configured. Docs and tests use prod and staging for the list form.
Do not put house hosts, house emails, KV ids, Access ids, or tokens in this repo. Deploy secrets stay in Wrangler secrets and .dev.vars (gitignored). Copy .dev.vars.example. Leave values empty in git.
Version
package.json version is the only source of truth. Cursor, Claude, and Codex plugin.json files, plus .claude-plugin/marketplace.json, src/server.ts MCP version, and package-lock.json root version, must match it. Plugin name, homepage, and license must match package.json too. After you bump package.json, copy the version into:
.cursor-plugin/plugin.json.claude-plugin/plugin.json.claude-plugin/marketplace.json(top-level and the plugin entry).codex-plugin/plugin.jsonsrc/server.ts(McpServerversion)package-lock.json(runnpm installso the lockfile root version updates)
Then run npm run ci. Do not open or push a PR until that command is green.
CI
npm run ci runs lint, typecheck, tests, and scripts/check-manifests.mjs. That script fails on version or name/homepage/license drift (plugin.json files, Claude marketplace, src/server.ts MCP version, lockfile root version), a missing or malformed marketplace entry, or SchemaStore validation failure for the Claude plugin, Claude marketplace, and Codex plugin manifests. GitHub Actions on push and pull_request runs the same npm run ci. A husky pre-push hook runs it locally so a red tree does not reach the remote.
Plugins and marketplaces
| Client | Plugin | Marketplace |
|---|---|---|
| Cursor | .cursor-plugin/plugin.json and .cursor-plugin/mcp.json |
Cursor plugin install from this repo |
| Claude Code | .claude-plugin/plugin.json |
.claude-plugin/marketplace.json |
| Codex / ChatGPT Work | .codex-plugin/plugin.json and .mcp.json |
.agents/plugins/marketplace.json |
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.
- today Changed · +29 tokens per session b185b2b4d396
- 3d ago First seen · 41 lines · 788 tokens per session scan A a88ffb35c8a5
bws-mcp AGENTS.md is an instructions file published in the GitHub repository bchoor/bws-mcp (2 stars, last pushed 2d ago), licensed MIT. It adds 817 tokens to every session, about $0.0041 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.