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/scorbo2/mcp-light/agents-mdgit clone --depth 1 https://github.com/scorbo2/mcp-lightWrote 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/scorbo2/mcp-light/agents-md)<a href="https://agentmods.dev/instructions/scorbo2/mcp-light/agents-md"><img src="https://agentmods.dev/badge/instructions/scorbo2/mcp-light/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 | $0.00516 | $0.00516 |
| Opus 5 | $0.00258 | $0.00258 |
| Sonnet 5 | $0.00103 | $0.00103 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
mcp-light AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Quick commands
| Task | Command |
|---|---|
| Build | mvn clean package |
| Run (default port 8080) | java -jar target/mcp-light-1.1.jar |
| Run (custom port) | java -jar target/mcp-light-1.1.jar 9090 |
| Tests | mvn test |
| Compile only | mvn compile |
Architecture
Single package ca.corbett.mcp. No framework — bare Java 25 + com.sun.net.httpserver + Jackson.
McpServer— HTTP server (port/path configurable). Registers tools/resources, routes JSON-RPC methods.McpTool— interface to implement for callable tools.execute()runs on the HTTP handler thread (synchronous).McpResource— interface to implement for readable resources.getContent()runs on the HTTP handler thread. Supports binary (base64) viaisBinary().McpPrompt— interface to implement for prompts.ExampleApp— runnable entry point with sample tool and resources. Set as main class in the jar manifest.
Gotchas
- Tool/resource/prompt names Tool/resource/prompt names must match
^[a-zA-Z0-9._-]+$and are treated as case-insensitively unique — enforced at registration and will throwIllegalArgumentExceptionfor invalid names. - Jackson is configured for case-insensitive property matching and ignoring unknown properties — MCP clients may send slightly malformed JSON.
- Port 0 in the constructor = random available port (useful for tests). Use
server.getPort()to discover it. McpServeris thread-safe for register/unregister viaCopyOnWriteArrayList.- GPG signing is skipped by default (
gpg.skip=true). Set tofalsefor Sonatype Central publishing. - Sonatype publishing is skipped by default (
skipPublishing=true). Set tofalseto enable. - Tests use port 0 and discover the actual port via
server.getPort(). Never hardcode a port in tests. - No lint, formatter, or typecheck steps beyond
mvn compile/mvn test. Code style follows IntelliJ defaults (.editorconfig).
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 · 33 lines · 516 tokens per session scan A 9c258c0aa5fc
mcp-light AGENTS.md is an instructions file published in the GitHub repository scorbo2/mcp-light (6 stars, last pushed 1mo ago), licensed MIT. It adds 516 tokens to every session, about $0.0026 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.