core: Instructions file for Claude Code

CLAUDE.md

core CLAUDE.md is an instructions file for Claude Code from sima-neat/core. It costs 3,227 tokens per session, scanned A, original, Apache-2.0.

A project instruction file for SiMa Neat, a C++20 library for building, checking, running, and debugging GStreamer pipelines, with Python bindings. It documents the repository, build commands, important code locations, and tests.

In plain words
What is it for?
Use it when developing, building, testing, documenting, or working with the C++ library and its Python bindings.
Why use it?
It gives coding agents the repository's operating rules and source-of-truth commands before they change or test the code.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is sima-neat/core's own configuration. It tells Claude Code how to work on core itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything core configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sima-neat/core. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sima-neat/core/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/sima-neat/core

Made for: Claude Code.

Wrote 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.

agentmods badge for core CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sima-neat/core/claude-md/github.svg)](https://agentmods.dev/instructions/sima-neat/core/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sima-neat/core/claude-md"><img src="https://agentmods.dev/badge/instructions/sima-neat/core/claude-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.

agentmods 80×15 button for core CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sima-neat/core/claude-md"><img src="https://agentmods.dev/badge/instructions/sima-neat/core/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,227 This file is loaded in full into every session.
When invoked 3,227 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.03227 $0.03227
Opus 5.5 $0.01291 $0.01291
Sonnet 5.5 $0.00645 $0.00645
Haiku 4.5 $0.00323 $0.00323

Measured 6d ago against content hash 66c1778239d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

core 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 6d 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.

CLAUDE.md · 337 lines

How it starts

The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude (and other agents) working in this repository.

This file complements AGENTS.md, CONTRIBUTING.md, and the authoritative contributor docs under docs/develop-apps/contribute/ — read those for full rationale. This file extracts the operational essentials.

What this repo is

SiMa Neat — a C++20 library for building, validating, running, and debugging GStreamer pipelines with a typed, composable API. Ships C++ libraries plus Python bindings (pyneat) built with nanobind + scikit-build-core.

  • C++ namespace: simaai::neat
  • CMake project: SimaNeat
  • Core runtime types: Model, Session, Run
  • Public API surface: headers under include/ (treated as stable)
  • Canonical production pipeline test (source of truth): tests/e2e_pipelines/obj_detection/sync_yolov8_test.cpp

Build commands

The single entrypoint is build.sh. Output lands under build/.

./build.sh                       # dev-only: core lib + headers (default)
./build.sh --all                 # lib + tests + tutorials + docs + pyneat wheel
./build.sh --all --clean         # clean full build
./build.sh --python              # add pyneat bindings to selected targets
./build.sh --doc                 # docs only
./build.sh --fuzz                # fuzz-enabled package artifacts
./build.sh --asan-ubsan          # ASan+UBSan instrumented build
./build.sh --tsan                # TSan instrumented build
./build.sh --install-deps-only   # bootstrap system deps, exit
./build.sh -h                    # full help

Under the hood: CMake 3.16+, CMAKE_CXX_STANDARD 20, Release by default. Key options surfaced as -DSIMANEAT_BUILD_* toggles in CMakeLists.txt.

Python bindings (pyneat)

python -m pip install -e .[dev]   # editable install with dev extras
pytest -q                          # runs python/tests and tests/tutorials

pyproject.toml declares the build (scikit-build-core + nanobind ≥ 2.4). Extension module is pyneat._pyneat_core. NumPy/PyTorch interop is via DLPack.

Read the full file on GitHub · 337 lines

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. 6d ago Changed 66c1778239d7
  2. 2mo ago First seen · 337 lines · 3,227 tokens per session scan A f4fed25208ce

Subscribe to this mod's changes

core CLAUDE.md is an instructions file published in the GitHub repository sima-neat/core (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,227 tokens to every session, about $0.0129 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.

Related

core CLAUDE.md compared with instructions from other repositories

core CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
core CLAUDE.mdsima-neat/coreInstructions file8yesterdayApache-2.0A3,227Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode