agentmods.dev

math-anchor CLAUDE.md

Project instructions for Math Anchor, a tool for exact and scientific calculations, units, and dimensional analysis.

In plain words
What is it for?
Use them when changing or reviewing Math Anchor's parsers, operations, errors, tests, packaging, or agent-facing interface.
Why use it?
They give coding agents the rules needed to keep calculations safe, results correctly labeled, and the human app and agent interface consistent.

Instructions file

0 6d ago A scan 140 tokens original Apache-2.0
View the source file tetracoralla/math-anchor
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/tetracoralla/math-anchor/claude-md
Clone the repo
git clone --depth 1 https://github.com/tetracoralla/math-anchor
Per session 140 This file is loaded in full into every session.
When invoked 140 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 $0.00140 $0.00140
Opus 5 $0.00070 $0.00070
Sonnet 5 $0.00028 $0.00028
Haiku 4.5 $0.00014 $0.00014

Measured today against content hash 006e5d092e5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

math-anchor 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 today.

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.

CLAUDE.md · 15 lines

What it actually says

Math Anchor Claude Code contract

@AGENTS.md

  • Resolve technical implementation decisions autonomously from current source, runtime behavior, and the repository contract. This includes numeric limits, schema/handler alignment, parser behavior, error codes, refactor boundaries, tests, packaging, and runtime verification.
  • Do not hand technical alternatives or raw implementation details to the owner for adjudication. Choose the smallest correct route, implement it, and report the result in plain language.
  • Ask the owner only for product value or direction, visible experience preference, release/deploy/publication intent, credentials, spending, legal/privacy exposure, or another genuinely owner-only authorization.
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. today First seen · 15 lines · 140 tokens per session scan A 006e5d092e5e

Subscribe to this mod's changes

math-anchor CLAUDE.md is an instructions file published in the GitHub repository tetracoralla/math-anchor (0 stars, last pushed 6d ago), licensed Apache-2.0. It adds 140 tokens to every session, about $0.0007 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.

LanguagesScientificTestingcalculatorcodex-pluginmathematicsmcpscientific-computingswiftui
Related

Other instructions, from other repositories

scholaraio AGENTS.md

Instructions for ZimoLiao/scholaraio, covering scholaraio - agent entry, what scholaraio is, how to work in this repo, start here and skill-first workflow.

ZimoLiao/scholaraio · 2,046 tokens

PyAutoArray CLAUDE.md

Instructions for PyAutoLabs/PyAutoArray: The canonical, agent-agnostic instructions live in AGENTS.md. Claude Code loads them via the import below; if your tool does not process @-imports, open AGENTS.md in this directory and read it directly. @AGENTS.md.

PyAutoLabs/PyAutoArray · 65 tokens

math-mcp-learning-server AGENTS.md

AGENTS.md instructions for clouatre-labs/math-mcp-learning-server, covering math mcp learning server - python mcp server [production], stack, structure, commands and project-specific patterns.

clouatre-labs/math-mcp-learning-server · 546 tokens

OpenSDL CLAUDE.md

Instructions for fl-sean03/OpenSDL, a project described as: A modular Python foundation for reproducible computational and autonomous laboratories. Alpha; the reference profile is simulator-only.

fl-sean03/OpenSDL · 5 tokens

relarena CLAUDE.md

Instructions for PriorLabs/relarena: All package notes live in AGENTS.md — read that first.

PriorLabs/relarena · 23 tokens

co-mathematician CLAUDE.md

Instructions for VeryMath/co-mathematician, covering claude.md, repository contract, required flow, claude code operating notes and harness commands.

VeryMath/co-mathematician · 902 tokens