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/dennisprediger/slac-mcp/agents-mdgit clone --depth 1 https://github.com/DennisPrediger/SLAC-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/dennisprediger/slac-mcp/agents-md)<a href="https://agentmods.dev/instructions/dennisprediger/slac-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/dennisprediger/slac-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 | $0.00435 | $0.00435 |
| Opus 5 | $0.00217 | $0.00217 |
| Sonnet 5 | $0.00087 | $0.00087 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
SLAC-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 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.
What it actually says
AGENTS.md
Project
Rust MCP server exposing SLAC (Simple Logic & Arithmetic Compiler) as tools via the Model Context Protocol.
- Single crate, edition 2024 (requires Rust 1.85+)
rmcp2.2.0 - official Rust MCP SDK (tokio-based)slac1.1.0 - expression-to-AST compiler with built-in tree-walk interpreter
Purpose
Provide LLM agents a simple way to evaluate logical and arithmetic expressions at runtime via the SLAC expression language.
Tools
evaluate(expression: string): string- Compiles and evaluates a SLAC expression, returns the result as a string.get_syntax(): string- Returns the full SLAC language reference (syntax, operators, functions, examples) viainclude_str!.
Non-Goals
- Exposing the compiled AST. SLAC supports this, but the MCP must not expose it.
Architecture
src/main.rs- MCP server bootstrap (tracing, stdio transport)src/server.rs-SlacServerunit struct with tool handlers andServerHandlerimplsrc/get-syntax.md- SLAC language reference included byget_syntax
Key Constraint: !Send Environment
slac::StaticEnvironment is !Send + !Sync (contains Rc internally). It cannot be stored in the service struct behind Arc<Mutex<>>. Each evaluate call creates a fresh environment: StaticEnvironment::default() -> extend_environment() -> compile() -> execute().
Environment Variables
OUTPUT_FORMAT=JSON- When set,evaluatereturns pretty-printed JSON viaserde_jsoninstead of the default RustDisplayrepresentation.
Build & Run
cargo build
cargo run
For testing with MCP Inspector:
npx @modelcontextprotocol/inspector cargo run
No test, lint, or CI configuration exists yet.
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 · 52 lines · 435 tokens per session scan A 2c2390f85835
SLAC-MCP AGENTS.md is an instructions file published in the GitHub repository DennisPrediger/SLAC-MCP (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 435 tokens to every session, about $0.0022 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
m1nd AGENTS.md
AGENTS.md instructions for maxkle1nz/m1nd, covering agents.md — working guide for any coding agent on m1nd, the gates (must pass — these are the ci), git identity — absolute, no-leak — reputation rule (public repo) and how work lands — bursts, not pr-per-fix.
blz AGENTS.md
Instructions for outfitter-dev/blz, covering blz repository instructions for ai agents, important, working memory, use blz and 🚀 quick start for agents.
rust-mcp-server copilot-instructions.md
Instructions for Vaiz/rust-mcp-server, covering copilot instructions for rust mcp server, project context, key guidelines, mcp protocol implementation and dependencies.
rusty_apple_mail_mcp AGENTS.md
AGENTS.md instructions for like-a-freedom/rusty_apple_mail_mcp, covering agents.md — rust development constitution, code navigation rules, 0. meta-rules for ai agents, quality gate (mandatory before every commit) and 1. format — must pass before anything else.
mcp-loxone CLAUDE.md
Claude Code instructions for avrabe/mcp-loxone, covering claude.md, 🦀 rust project overview, 🛠️ common development commands, setup & installation and install rust toolchain (if needed).
plc-toolkit CLAUDE.md
Claude Code instructions for Adjoint-uk/plc-toolkit, covering claude.md, project, status, build and structure.