agentmods.dev

face-detect.cpp AGENTS.md

A contributor guide for face-detect.cpp, a C++ program that finds and recognises faces in images. It explains the project structure, how to build it, and how people should review and credit AI-assisted code.

In plain words
What is it for?
Building and contributing to face-detect.cpp, including understanding its image-processing pipeline, repository layout, and requirements for commits containing AI-assisted changes.
Why use it?
It gives developers and coding agents the project rules they need before changing the code. This helps avoid incorrect contribution records and misunderstandings about how the software works.

Instructions file for CodexOpenCode

24 2mo ago A scan 1,571 tokens original MIT
View the source file mudler/face-detect.cpp
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/mudler/face-detect.cpp/agents-md
Clone the repo
git clone --depth 1 https://github.com/mudler/face-detect.cpp

Made for: Codex, OpenCode.

Per session 1,571 This file is loaded in full into every session.
When invoked 1,571 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 $0.01571 $0.01571
Opus 5 $0.00785 $0.00785
Sonnet 5 $0.00314 $0.00314
Haiku 4.5 $0.00157 $0.00157

Measured yesterday against content hash 5a69e5695a12, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

face-detect.cpp 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.

AGENTS.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contributor & agent guide

This is the working guide for humans and AI coding assistants on face-detect.cpp.

AI-assisted contributions

face-detect.cpp follows the Linux kernel project's guidelines for AI coding assistants. Before submitting AI-assisted code:

  • No Signed-off-by from an AI. Only the human submitter signs off on the Developer Certificate of Origin (DCO). Every commit must carry the human's Signed-off-by: trailer.
  • No Co-Authored-By: <AI> trailers. The human contributor owns the change.
  • Use an Assisted-by: trailer to attribute AI involvement. Format: Assisted-by: AGENT_NAME:MODEL_VERSION [TOOL].
  • The human submitter is responsible for reviewing, testing, and understanding every line of generated code.

What this project is

A standalone C++17/ggml face-recognition engine with GGUF weights, consumed by LocalAI through a flat C ABI (dlopen/purego). It replaces LocalAI's Python insightface backend. Pipeline: decode image -> SCRFD detect -> 5-landmark align (insightface norm_crop) -> ArcFace embed -> L2-normalized 512-d embedding, plus verify / analyze / detect and an optional MiniFASNet anti-spoof veto.

Repository layout

include/           public headers: facedetect.h, facedetect_capi.h (the frozen ABI)
src/               flat .cpp/.hpp stages:
  facedetect.cpp     version + fd:: convenience layer
  facedetect_capi.cpp flat C-ABI implementation
  model.{cpp,hpp}    load-once orchestration (detect/embed/analyze)
  model_loader.*     GGUF KV + tensor reader (facedetect.* namespace)
  backend.*          persistent ggml_backend_t + gallocr wrapper (+ global_backend)
  image_io.*         image decode to RGB (libjpeg-turbo for JPEG = cv2.imread
                     parity; vendored stb_image for PNG/BMP + fallback)
  align.*            norm_crop 5-landmark similarity transform (TODO)
  detect.*           SCRFD anchor decode + NMS, host-side (NMS done; decode TODO)
examples/cli/      facedetect-cli (info/embed/detect/verify/analyze/bench)
tests/             parity.hpp harness + ctest targets + python/check_convert.py
scripts/           convert_facedetect_to_gguf.py, gen_baseline.py, requirements.txt,
                   apply_ggml_patches.sh
docs/              conversion.md, parity.md, quantization.md
third_party/       ggml submodule + vendored stb_image.h + ggml-patches/
models/            MANIFEST.md (the GGUFs themselves are git-ignored)

Read the full file on GitHub · 135 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. yesterday First seen · 135 lines · 1,571 tokens per session scan A 5a69e5695a12

Subscribe to this mod's changes

face-detect.cpp AGENTS.md is an instructions file published in the GitHub repository mudler/face-detect.cpp (24 stars, last pushed 2mo ago), licensed MIT. It adds 1,571 tokens to every session, about $0.0079 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 2026-08-30.

Code reviewPlanning
Related

Other instructions, from other repositories

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

buildNext

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

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

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

spec-kit 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 · 7,040 tokens

langchain 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