Borrowing it
Nothing to install: this file belongs to tensorcircuit/tensorcircuit-ng. 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/tensorcircuit/tensorcircuit-ng/master/AGENTS.mdgit clone --depth 1 https://github.com/tensorcircuit/tensorcircuit-ngWrote 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/tensorcircuit/tensorcircuit-ng/agents-md)<a href="https://agentmods.dev/instructions/tensorcircuit/tensorcircuit-ng/agents-md"><img src="https://agentmods.dev/badge/instructions/tensorcircuit/tensorcircuit-ng/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/tensorcircuit/tensorcircuit-ng/agents-md"><img src="https://agentmods.dev/badge/instructions/tensorcircuit/tensorcircuit-ng/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 | $0.01462 | $0.01462 |
| Opus 5.5 | $0.00585 | $0.00585 |
| Sonnet 5.5 | $0.00292 | $0.00292 |
| Haiku 4.5 | $0.00146 | $0.00146 |
Grade A, and why
tensorcircuit-ng 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 26d 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TensorCircuit-NG Repository Guide for AI Agents
Mission
TensorCircuit is a tensor-network-first, multi-backend quantum computing framework. Optimize for backend-agnostic, differentiable, JIT-friendly code changes that match existing repository style.
Non-Negotiable Rules
- Use
tc.backendfor core tensor operations. Do not call backend-specific APIs such as NumPy, JAX, or TensorFlow directly in core logic. - Prefer backend-native abstractions already used in the repo, including
tc.backend.jit,tc.backend.grad,tc.backend.vmap, and backend control-flow helpers when applicable. - Preserve differentiability. Avoid graph-breaking conversions, in-place tensor mutation, and other patterns that block autodiff.
- Preserve JIT compatibility. Avoid Python control flow that depends on tensor values; prefer backend control-flow helpers or static structure.
- Keep changes minimal and consistent with existing architecture.
- Prefer simple, direct implementations. Avoid defensive complexity and broad
try...exceptblocks. - Fail fast. Expose real problems early instead of masking them with silent fallbacks or workaround-heavy logic.
- Do not cheat around repository invariants, tests, or framework behavior just to make a local change appear to pass.
- Focus only on git-tracked files. Do not search for or modify files in
.gitignoreunless explicitly specified by the user. tensorcircuit/applicationsandbenchmarks/are deprecated, do not add or modify files there unless the user explicitly specified.
Environment Rules
- Never install packages into system or user Python unless the user explicitly asks.
- If a command fails because of missing Python packages or
ModuleNotFoundError, ask the user which environment to use. - Once the environment is known, run Python tooling through that environment, for example
conda run -n <env> .... - Dependency and tool configuration lives in
requirements/,pyproject.toml, and.pylintrc. - Keep sandbox- or machine-specific execution workarounds out of tracked source files unless the user explicitly asks for a repo-level workaround. Examples include redirecting
MPLCONFIGDIR, cache directories, or other local writable paths just to satisfy the current sandbox. - Do not hardcode or publicly expose local conda environment names, usernames, absolute paths, hostnames, or other machine-specific execution details in tracked docstrings, examples, or user-facing scripts. Use generic placeholders such as
conda run -n <env> ...unless the repository explicitly needs a concrete value.
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.
- 26d ago Changed · +6 lines · +144 tokens per session a5f805f044fe
- 27d ago Changed · +1 lines · +27 tokens per session edaa02b57d71
- 2mo ago First seen · 72 lines · 1,291 tokens per session scan A c8c249818416
tensorcircuit-ng AGENTS.md is an instructions file published in the GitHub repository tensorcircuit/tensorcircuit-ng (93 stars, last pushed today), licensed Apache-2.0. It adds 1,462 tokens to every session, about $0.0058 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.