symkit-mcp AGENTS.md

symkit-mcp AGENTS.md is an instructions file for Codex, OpenCode from LBurny/symkit-mcp. It costs 1,728 tokens per session, scanned A, original, Apache-2.0.

A set of instructions for SymKit MCP, a server that lets AI assistants perform symbolic mathematics with SymPy. Symbolic mathematics works with formulas and exact derivation steps rather than only calculating decimal answers.

In plain words
What is it for?
Use it when building, testing, or debugging formula operations, step-by-step derivation sessions, persistence, or external data adapters. MCP is a standard way for AI tools to call external services.
Why use it?
It explains the server's tool layout, domain boundaries, and session storage so changes do not mix mathematical logic with the AI connection layer.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/lburny/symkit-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/LBurny/symkit-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for symkit-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lburny/symkit-mcp/agents-md.svg)](https://agentmods.dev/instructions/lburny/symkit-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/lburny/symkit-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/lburny/symkit-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,728 This file is loaded in full into every session.
When invoked 1,728 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01728 $0.01728
Opus 5 $0.00864 $0.00864
Sonnet 5 $0.00346 $0.00346
Haiku 4.5 $0.00173 $0.00173

Measured 5d ago against content hash cc0c3855bcd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

symkit-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 5d 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.

AGENTS.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Workspace instructions for ZCode agents working in nsforge-mcp-sigma.

Repository Purpose

SymKit MCP (symkit-mcp) — a FastMCP server exposing ~43 MCP tools for symbolic formula derivation over SymPy. Domain-agnostic: physics, engineering, chemistry, biology, economics. The server runs over MCP stdio; AI agents (Claude, etc.) are the clients.

Entry point: src/symkit_mcp/server.pysymkit-mcp console script. The single math() tool covers ~25 symbolic operations; session_* tools manage step-by-step derivations with full provenance persisted to derivation_sessions/.

Major Directories

  • src/symkit/ — Core domain library (DDD-layered, no MCP dependency)
    • domain/ — Pure business logic, entities, value objects, services. Must not import external/infra modules.
    • application/ — Use cases coordinating Domain ↔ Infrastructure.
    • infrastructure/ — SymPy engine, file persistence, external adapters (Wikidata, SciPy, BioModels).
    • resources/ — Static resources.
  • src/symkit_mcp/ — MCP presentation layer
    • server.py — FastMCP entry; eagerly initializes SessionManager in a worker thread on startup (see Gotchas).
    • tools/ — Tool implementations grouped by concern: math.py, session.py, formula.py, codegen.py, symbols.py, assumptions.py, orchestration.py. All register via register_all_tools(mcp) in __init__.py.
    • tools/_state.pyProcess-global shared state: single _current_session and _current_context. All tool modules read/write through get_session()/set_session()/get_context()/set_context().
  • formulas/ — YAML formula library (library/<category>/*.yaml) and derived/ outputs (gitignored).
  • derivation_sessions/ — Persisted session JSON (gitignored runtime artifacts).
  • tests/ — pytest suite, phase-organized (test_phase1_*test_phase5_*) plus domain/engine/parser suites. E2E MCP smoke tests (test_mcp_e2e.py, test_mcp_minimal.py) spawn the server in stdio mode via the MCP client SDK.
  • docs/ — Design docs (symkit-design.md, composable-formula-modification-engine.md, etc.).
  • .github/bylaws/ — Binding sub-laws: ddd-architecture.md, git-workflow.md, python-environment.md.

Read the full file on GitHub · 80 lines

Changes

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.

  1. 5d ago First seen · 80 lines · 1,728 tokens per session scan A cc0c3855bcd9

Subscribe to this mod's changes

symkit-mcp AGENTS.md is an instructions file published in the GitHub repository LBurny/symkit-mcp (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,728 tokens to every session, about $0.0086 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.

Related

Other instructions, from other repositories

bio-gene-to-reference-tree copilot-instructions.md

Copilot instructions for Hongda-Zhao/bio-gene-to-reference-tree, a project described as: Auditable agent skill for resolving protein queries, selecting references, and planning reproducible phylogenetic trees.

Hongda-Zhao/bio-gene-to-reference-tree · 105 tokens

braina GEMINI.md

Instructions for brainets/braina, covering project: braina (brain interaction analysis), 1. project context & purpose, 2. commands, verify environment (all core dependencies) and run the verification test suite for frites + hoi.

brainets/braina · 1,269 tokens

research-automation CLAUDE.md

Instructions for lucafusarbassini/research-automation, covering ricet - research automation framework, project overview, claude-flow mcp, workflow habits and file organization.

lucafusarbassini/research-automation · 904 tokens

shannon-prover CLAUDE.md

Claude Code instructions for SkyShannonProver/shannon-prover, covering shannon prover: claude entry point, current boundary, easycrypt environment, eval safety and current documentation.

SkyShannonProver/shannon-prover · 586 tokens

SciCrucible CLAUDE.md

Claude Code instructions for Xinyang-Li666/SciCrucible, covering 科学知识库, 知识库结构, 可用命令, 项目目录 and 工作原则.

Xinyang-Li666/SciCrucible · 1,107 tokens

torchcell CLAUDE.md

Claude Code instructions for Mjvolk3/torchcell, covering vision -- the virtual cell (north star), for local configs, git worktrees, programming guide and provenance & reproducibility.

Mjvolk3/torchcell · 12,957 tokens