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/confluentinc/mcp-confluent/copilot-instructionsgit clone --depth 1 https://github.com/confluentinc/mcp-confluentWrote 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/confluentinc/mcp-confluent/copilot-instructions)<a href="https://agentmods.dev/instructions/confluentinc/mcp-confluent/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/confluentinc/mcp-confluent/copilot-instructions.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 | $0.03607 | $0.03607 |
| Opus 5 | $0.01803 | $0.01803 |
| Sonnet 5 | $0.00721 | $0.00721 |
| Haiku 4.5 | $0.00361 | $0.00361 |
Grade A, and why
mcp-confluent copilot-instructions.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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-confluent
Project Overview
MCP (Model Context Protocol) server that exposes Kafka-ecosystem and Confluent tooling to AI assistants. The tool surface splits into two groups:
- Kafka-protocol tools that work against any Apache Kafka®-compatible cluster or Schema Registry (e.g., topic CRUD, producing and consuming messages, schema management).
- Confluent Cloud-specific tools that wrap CCloud REST APIs (e.g., Flink, Tableflow,
billing), enabled only when the relevant service block (
confluent_cloud:,flink:,tableflow:) is present in a connection's resolved config (from YAML or, during the migration, legacy env vars + CLI args).
Built with TypeScript, Node.js ≥22.19.0, and the @modelcontextprotocol/sdk. Ships as an npm package
and a Docker image; supports stdio, Streamable HTTP, and (for backwards compatibility with older
MCP clients) the legacy HTTP+SSE transport.
These instructions exist to keep GitHub Copilot PR reviews focused on the invariants that matter in
this codebase. Author-facing guidance (how to scaffold a tool, run the inspector, etc.) lives in
CONTRIBUTING.md and CLAUDE.md — refer to those rather than repeating them here.
Architecture (what reviewers need to know)
Entry flow
At startup: parseCliArgs() → initEnv() → branch on whether -c <path> was supplied:
loadConfigFromYaml(path, process.env) for the YAML path, or buildConfigFromEnvAndCli(env, ...)
for the legacy env+CLI path. Both return a single MCPServerConfiguration. Then
ServerRuntime.fromConfig() constructs one DirectClientManager per connection → iterates
ToolName enum to build the enabled tool set → registers tools on McpServer → starts transports.
YAML (-c <path>) is the preferred path. The env-var-only path is legacy: parity remains for a
single connection in this release, but it's slated for a startup warning in a near-future release
and removal a release or two later. Don't approve new code that reaches back into the legacy
synthesizer or assumes env-only configuration as the canonical model. User-facing version of this
story: CONFIGURATION.md at the repo root.
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.
- 4d ago First seen · 240 lines · 3,607 tokens per session scan A e6ac0c416b63
mcp-confluent copilot-instructions.md is an instructions file published in the GitHub repository confluentinc/mcp-confluent (167 stars, last pushed 4d ago), licensed MIT. It adds 3,607 tokens to every session, about $0.0180 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 2026-08-30.
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.