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/wspringer/highs-mcp/claude-mdgit clone --depth 1 https://github.com/wspringer/highs-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/wspringer/highs-mcp/claude-md)<a href="https://agentmods.dev/instructions/wspringer/highs-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/wspringer/highs-mcp/claude-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 | $0.00395 | $0.00395 |
| Opus 5 | $0.00198 | $0.00198 |
| Sonnet 5 | $0.00079 | $0.00079 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
highs-mcp CLAUDE.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.
What it actually says
Project Overview
This is an MCP server offering HiGHS optimization tools to LLMs.
Knope
In this project, we're keeping track of changes using Knope. Claude itself is
not capable of using the knope tool, so whenever we want Claude to define a
changeset, it needs to build it by hand. Here are some of the rules to take into
account:
-
Changeset files live in the
.changesetdirectory. -
Changeset files must have a unique name.
-
Typically the name of the file is snake-cased, lower characters, with a
.mdsuffix. -
Knope typically generates a file that is based on the first readable line in the body description of the changeset, abbreviating it, lowercasing it all and snake-casing it. It wouldn't hurt to maintain that convention.
-
The body of the markdown file typically starts with a one line summary of the change, formatted as a title.
# Add support for version 3.0 of jquery -
The frontmatter should look like this:
--- default: major|minor|patch --- -
The specific type: 'major', 'minor', or 'patch' should be based on an assesment of the character of the changes that are documented in that changeset.
- Breaking changes: 'major'
- Feature enhancements: 'minor'
- Bug fixes and alike: 'patch'
Feature example
---
default: minor
---
# Add sparse matrix support
Implemented COO format sparse matrix handling for improved memory efficiency
with large optimization problems.
Breaking change example
---
default: major
---
# Restructure MCP server API endpoints
Renamed optimization endpoints and changed request/response format
for better consistency with MCP standards.
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.
- 5d ago First seen · 64 lines · 395 tokens per session scan A 4e583ce9b74c
highs-mcp CLAUDE.md is an instructions file published in the GitHub repository wspringer/highs-mcp (18 stars, last pushed 1y ago), licensed MIT. It adds 395 tokens to every session, about $0.0020 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
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.
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.
research-automation CLAUDE.md
Instructions for lucafusarbassini/research-automation, covering ricet - research automation framework, project overview, claude-flow mcp, workflow habits and file organization.
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.
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.
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.