core AGENTS.md

Baseline contribution instructions for the sima-neat core project, covering coding standards, testing, public API compatibility, documentation, and installation rules for internal runtime files.

In plain words
What is it for?
Use it when modifying the core library, public headers, architecture or user documentation, examples, or generated NEAT runtime and plugin .so files.
Why use it?
It helps changes follow the project’s required review and compatibility rules, especially when public headers or internal shared-library files are changed.

Instructions file for CodexOpenCode

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/sima-neat/core/agents-md
Clone the repo
git clone --depth 1 https://github.com/sima-neat/core

Made for: Codex, OpenCode.

Per session 731 This file is loaded in full into every session.
When invoked 731 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 $0.00731 $0.00731
Opus 5 $0.00365 $0.00365
Sonnet 5 $0.00146 $0.00146
Haiku 4.5 $0.00073 $0.00073

Measured 2d ago against content hash 17a5bdc16c28, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

core 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 2d 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.

AGENTS.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guidance

This file defines baseline quality expectations for automated and human contributors.

Required standards

  • Follow the coding rules in docs/develop-apps/contribute/start-here/coding_standard.md.
  • Follow the testing rules in docs/develop-apps/contribute/build-test/test_requirements.md.
  • Treat public headers under include/* as stable API.

API compatibility

  • Prefer non-breaking API changes.
  • Any breaking public API signature change must follow the documented process in docs/develop-apps/contribute/start-here/coding_standard.md.
  • PRs with breaking API changes must complete the Breaking API Change section in .github/pull_request_template.md.

Documentation updates

When behavior or public API changes:

  • Update docs/develop-apps/contribute/start-here/architecture.md if architecture/contracts changed.
  • Update user-facing docs for workflow/configuration changes.
  • Update examples if API usage changed.

Internals install contract

When changing or rebuilding anything under internals/ that produces NEAT runtime/plugin .so files:

  • Treat /usr/lib/aarch64-linux-gnu/neat/gst-plugins and /usr/lib/aarch64-linux-gnu/neat/runtime as the canonical runtime roots.
  • Configure the internals/ build for the canonical Debian multiarch install layout: cmake -S internals -B <internals-build-dir> -DCMAKE_INSTALL_PREFIX=/usr -DCMAKE_INSTALL_LIBDIR=lib/aarch64-linux-gnu.
  • After cmake --build <internals-build-dir>, always run cmake --install <internals-build-dir> before rebuilding or testing core/.
  • Do not rely on internals/build/artifacts/gst-plugins as the default runtime source for core; build-tree plugin use should be an explicit override for debugging only.
  • For aarch64 test binaries, use dk or the repo devkit wrappers instead of local execution.

Preproc and MPK contract invariants

When editing route planning, modelpack contract usage, or processcvu/preproc config projection:

  • Treat *_mpk.json as the source of truth for inference-side contracts (MLA ingress/egress tensors, postprocess/inference transforms, tensor dtypes/shapes/routing).
  • When inspecting a model .tar.gz or extracted model pack, read only the MPK manifest JSON (mpk.json / *_mpk.json).
  • Ignore every other JSON inside the model archive or extracted model tree; do not derive contracts, routing, geometry, preprocess, or postprocess behavior from them.
  • If the MPK manifest JSON is missing, treat that as a contract error instead of falling back to other JSON files.
  • Do not treat MPK MLA ingress shape as a hard cap for preproc input image size.
  • Preproc input is user/runtime-defined and may be larger than model ingress; preproc is responsible for dynamic resize.
  • Preproc output must match model/inference ingress expectations (for example, resize to 640x640 when that is the model input contract).
  • quant, tess, and quanttess are shape-preserving transforms; they do not perform spatial resize.

Read the full file on GitHub · 58 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. 2d ago First seen · 58 lines · 731 tokens per session scan A 17a5bdc16c28

Subscribe to this mod's changes

core AGENTS.md is an instructions file published in the GitHub repository sima-neat/core (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 731 tokens to every session, about $0.0037 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.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 6,785 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens