Borrowing it
Nothing to install: this file belongs to dfieser/hea-bench. 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/dfieser/hea-bench/main/AGENTS.mdgit clone --depth 1 https://github.com/dfieser/hea-benchWrote 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/dfieser/hea-bench/agents-md)<a href="https://agentmods.dev/instructions/dfieser/hea-bench/agents-md"><img src="https://agentmods.dev/badge/instructions/dfieser/hea-bench/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/dfieser/hea-bench/agents-md"><img src="https://agentmods.dev/badge/instructions/dfieser/hea-bench/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 | $0.08305 | $0.08305 |
| Opus 5.5 | $0.03322 | $0.03322 |
| Sonnet 5.5 | $0.01661 | $0.01661 |
| Haiku 4.5 | $0.00830 | $0.00830 |
Grade A, and why
hea-bench 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 612 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Machine-oriented usage guide for hea-bench. If you are an AI coding
agent integrating this library into another project, read this first.
It tells you the public API, exact return types and units, the
fastest path to each common task, and the mistakes to avoid. Every
snippet here is copy-pasteable and was checked against the shipped
code.
Editing this repo's own docs (or this file)? Follow the writing rule in CONTRIBUTING.md: minimize jargon and explain any necessary term inline in plain language, and always state what a number is and its units. Don't defer to a glossary.
What this is
hea-bench is an open, interpretable calculator of the standard
high-entropy-alloy (HEA) thermodynamic and geometric descriptors plus
the canonical empirical phase-prediction rules. Every descriptor is
a transparent closed-form expression over a curated element-property
table. The fitted predictions (hardness, phase prediction sets) carry
calibrated uncertainty and a flag for alloys unlike their training data.
One calculation core, four parts, and every feature is in all four (owner rule, 2026-10-06), so point each person at whichever part suits them:
- Python library + CLI: this package (
pip install hea-bench, orpip install "hea-bench[all]"for the fitted models and the MCP server too). - MCP server:
pip install "hea-bench[mcp]", then runhea-bench-mcp(stdio), oruvx --from "hea-bench[mcp]" hea-bench-mcp. Twenty-four tools over this same library: the calculator (parse_composition, batchalloy_descriptorswith the Miedema enthalpies andalloy_rules, both taking custom elements and pair values,omega_sensitivity,oxide_report,ceramic_report,element_data,element_coverage), the dataset (corpus_build,corpus_query,corpus_describe,corpus_export,measured_properties), predictions (predict_properties,predict_phase_set,check_applicability), design (design_search,campaign_suggest), the benchmark (benchmark_summary,benchmark_run,benchmark_folds,benchmark_score,coverage_study) andabout, which reports what is available. Every response carries units or uncertainty fields, a citation key where a parametrization is involved, and the library version. If you are an agent with MCP support, prefer those tools over reimplementing the formulas below. Without MCP support, use the Python API, which is identical. - Web app: https://dfieser.github.io/hea-bench/, built from
web/. The calculator (alloys, oxides, ceramics, property and phase predictions), the Dataset, Design and Benchmark tabs. Point a person who does not code here. - Desktop app: one portable offline exe that is the web app in a Tauri window.
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.
- yesterday Changed · +7 lines · +28 tokens per session 3266de66bd06
- 1mo ago Changed · +5 lines · +91 tokens per session e71febcbedf7
- 1mo ago Changed · +75 lines · +1,221 tokens per session 63017320e17b
- 1mo ago Changed · +8 lines · +140 tokens per session 4eed6b9e98ed
- 2mo ago First seen · 517 lines · 6,825 tokens per session scan A 47c446598d9e
hea-bench AGENTS.md is an instructions file published in the GitHub repository dfieser/hea-bench (3 stars, last pushed yesterday), licensed MIT. It adds 8,305 tokens to every session, about $0.0332 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.
hea-bench AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hea-bench AGENTS.mddfieser/hea-bench | Instructions file | 3 | yesterday | MIT | A | 8,305 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| 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 |