Borrowing it
Nothing to install: this file belongs to tetracoralla/math-anchor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tetracoralla/math-anchor/main/AGENTS.mdgit clone --depth 1 https://github.com/tetracoralla/math-anchorWrote 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/tetracoralla/math-anchor/agents-md)<a href="https://agentmods.dev/instructions/tetracoralla/math-anchor/agents-md"><img src="https://agentmods.dev/badge/instructions/tetracoralla/math-anchor/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/tetracoralla/math-anchor/agents-md"><img src="https://agentmods.dev/badge/instructions/tetracoralla/math-anchor/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00336 | $0.00336 |
| Opus 5.5 | $0.00134 | $0.00134 |
| Sonnet 5.5 | $0.00067 | $0.00067 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
math-anchor 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 1mo 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
Math Anchor repository contract
Read docs/product-model.md and docs/REVIEW_CONTRACT.md before changing or reviewing the product surface.
For a requested review, read docs/REVIEW_CONTRACT.md within the requested
scope and follow the relevant source and dependencies. It records known risks,
not an exhaustive search plan. Report concrete cross-repository implications
when found. Review is read-only unless fixes are also requested; this entrypoint
does not dispatch another reviewer.
- Keep the human macOS app and the Agent interface on one calculation core.
- Keep Agent discovery, schemas, runtime metadata, and protocol concepts out of the human calculator UI.
- Keep the public MCP surface to
math.search,math.describe,math.run, andmath.batch; add capabilities to the operation registry, not as more public tools. - Never evaluate input with Python
eval,exec, stringsympify, orparse_expr. Extend the explicit AST translator when new expression syntax is required. - Preserve exact and approximate results as separate fields. Never label a floating approximation as exact.
- Add a negative regression test for parser, validation, timeout, and error-path fixes.
- Treat mathematical semantics, parser/schema alignment, internal bounds, error codes, refactors, tests, packaging, and runtime verification as Agent-owned technical closure. Decide from current source and executable behavior; do not ask the owner to choose among implementation details. Ask only for a plain-language product-direction or external-authorization decision.
- Report development regression, MCP/runtime user flow, and human experience acceptance separately.
- Do not commit or push unless the owner explicitly asks.
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.
- 1mo ago Changed · -8 tokens per session ac3434cb4e63
- 2mo ago First seen · 20 lines · 344 tokens per session scan A f8e6c1e4290e
math-anchor AGENTS.md is an instructions file published in the GitHub repository tetracoralla/math-anchor (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 336 tokens to every session, about $0.0013 per session on Opus 5.5. 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.
math-anchor AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| math-anchor AGENTS.mdtetracoralla/math-anchor | Instructions file | 0 | 1mo ago | Apache-2.0 | A | 336 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |