Borrowing it
Nothing to install: this file belongs to nimbus-agent/nimbus-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.
curl -O https://raw.githubusercontent.com/nimbus-agent/nimbus-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/nimbus-agent/nimbus-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/nimbus-agent/nimbus-mcp/claude-md)<a href="https://agentmods.dev/instructions/nimbus-agent/nimbus-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nimbus-agent/nimbus-mcp/claude-md/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.
<a href="https://agentmods.dev/instructions/nimbus-agent/nimbus-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nimbus-agent/nimbus-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01640 | $0.01640 |
| Opus 5.5 | $0.00656 | $0.00656 |
| Sonnet 5.5 | $0.00328 | $0.00328 |
| Haiku 4.5 | $0.00164 | $0.00164 |
Grade A, and why
nimbus-mcp CLAUDE.md scanned grade A with 1 finding 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 23d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -s -o /dev/null -w '%{http_code}' -L <url>`; the site serves real 404s, so the How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nimbus-mcp — Claude Code Context
What this is
@nimbus-dev/mcp — the MIT-licensed launcher that exposes a locally-installed
Nimbus index and its agents to any MCP client. It does no work itself: it locates the
nimbus binary already on the machine and execs it as nimbus mcp-server --stdio,
then passes stdio straight through.
The MCP server is not in this repo. It lives in the AGPL monorepo at
packages/cli/src/commands/mcp-server.ts + packages/cli/src/mcp/, and serves 21
tools: nine read-only index tools (INDEX_TOOL_SPECS) plus twelve agent-classified ones
(AGENT_CLASSIFIED_TOOL_SPECS — the eleven AGENT_TOOL_SPECS entries plus peekWhy).
This package only knows how to find the binary — never how to run the gateway.
Re-derive those numbers from packages/cli/src/mcp/adapter.ts before restating them.
adapter.test.ts pins the total (21), the nine index-tool names and the agent-classified
count (12), but nothing pins prose: this file said "six index tools" long after the list
grew to nine.
Stack
- Runtime: Bun, at the release pinned in
.bun-version(CI installs the same one) · Language: TypeScript 7.x strict · Linter: Biome - The published bin runs under Node, not Bun. It is built with
--target nodebehind a#!/usr/bin/env nodeshebang, and CI smoke-tests the builtdist/index.jsunder Node. Bun is only the dev and test toolchain. - Zero runtime dependencies. Not "few" — zero.
package.jsonhasdevDependenciesonly. Adding a runtime dep is a licence and supply-chain decision, not a convenience call. - No
any— useunknownfor external data; strict mode is non-negotiable.
Commands
bun run typecheck # tsc --noEmit
bun run lint # biome check .
bun run test # bun test
bun run test:coverage # lcov -> coverage/lcov.info; what the SonarCloud gate consumes
bun run build # dist/index.js (ESM, node target)
Cross-repo relationships
Nimbus— the gateway/CLI monorepo. Owns the MCP server this launcher starts, and owns the installer whose output directoriessrc/installer-contract.tsvendors. This package was extracted from it (packages/mcp-launcher) on 2026-08-20.
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.
- 23d ago Changed · +14 lines · +261 tokens per session 8a8eb487173e
- 1mo ago First seen · 87 lines · 1,379 tokens per session scan A 356aeabd4960
nimbus-mcp CLAUDE.md is an instructions file published in the GitHub repository nimbus-agent/nimbus-mcp (0 stars, last pushed 23d ago), licensed MIT. It adds 1,640 tokens to every session, about $0.0066 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.