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.
npx agentmods add instructions/quantumaikr/quant.cpp/claude-mdgit clone --depth 1 https://github.com/quantumaikr/quant.cppWhat 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 | $0.02450 | $0.02450 |
| Opus 5 | $0.01225 | $0.01225 |
| Sonnet 5 | $0.00490 | $0.00490 |
| Haiku 4.5 | $0.00245 | $0.00245 |
Grade A, and why
quant.cpp 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 today.
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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
quant.cpp — Agent Development Guide
Project Vision
"LLM의 SQLite" — 가장 작고, 가장 읽기 쉽고, 가장 쉽게 임베딩할 수 있는 LLM 엔진.
Two directions:
- Embedding Engine: quant.h 단일 헤더(15K LOC)로 어디든 LLM 추가
- KV Compression Research: 함수 3개로 새 양자화 타입 추가 가능한 연구 플랫폼
Non-goals: GPU 속도 경쟁 (llama.cpp 영역), 배치 서빙 (vLLM 영역), 학습
Project Overview
quant.cpp is a minimal C inference engine for local LLM with KV cache compression. 72K LOC, pure C, zero dependencies. Supports 7 architectures via GGUF. Killer feature: KV cache compression — 7x compression with PPL +0.0% vs FP32. Ships as quant.h (15K LOC single header) and WASM (192KB).
Architecture
include/turboquant/ — Public C API (turboquant.h, tq_types.h, tq_spec.h)
src/core/ — Algorithms (tq_polar.c, tq_qjl.c, tq_turbo.c, tq_uniform.c, tq_traits.c)
src/cache/ — Paged cache + progressive compression
src/backend/cpu/ — CPU kernels (generic, AVX2, NEON)
src/backend/cuda/ — CUDA kernels
src/backend/metal/ — Metal compute shaders (7 kernels: matmul, rmsnorm, rope, attention, etc.)
src/engine/ — GGUF loader, transformer forward, tokenizer, generate
tests/ — Google Test unit tests (34 tests)
wasm/ — Browser demo (quant.wasm 192KB + index.html)
docs/ — API reference, custom quantization guide, tech report
examples/ — Embedding examples (minimal, chat, kv_compare)
bench/ — Performance benchmarks
spec/ — Format specification + test vectors
integrations/ — llama.cpp, vLLM, Python bindings
harness/ — Autonomous development harness (run.sh, team.toml)
Key Documents
docs/prd_v0.1.md— Full product requirementsdocs/wbs_v0.1.md— Work breakdown structure with checklistsprogram.md— Current agent task specification (READ THIS FIRST)score.sh— Automated 5-dimension scoring (0.0 ~ 1.0)
Reference Implementations (DO NOT MODIFY)
refs/QJL/— QJL Python/CUDA implementation (Amir Zandieh)refs/PolarQuant/— PolarQuant Python/Triton implementationrefs/llama.cpp/— llama.cpp fork with TQ1/TQ2 weight quantizationrefs/vllm/— vLLM KV cache infrastructurerefs/onnx/— ONNX quantization operator specification
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.
- today First seen · 217 lines · 2,450 tokens per session scan A 920656ca7edd
quant.cpp CLAUDE.md is an instructions file published in the GitHub repository quantumaikr/quant.cpp (399 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 2,450 tokens to every session, about $0.0123 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 2026-09-01.
Other instructions, from other repositories
lemonade AGENTS.md
Instructions for lemonade-sdk/lemonade, covering agents.md, project overview, architecture, executables and backend abstraction.
plano CLAUDE.md
Instructions for katanemo/plano, covering claude.md, build & test commands, rust — wasm plugins (must target wasm32-wasip1), rust — brightstaff binary (native target) and rust — tests, format, lint.
neuron-ai AGENTS.md
Instructions for neuron-core/neuron-ai, covering neuron ai - project overview, the mental model: neuron is a composable workflow, development commands, architecture and modules.
neuron-ai CLAUDE.md
Instructions for neuron-core/neuron-ai, covering project overview, code standards, think before coding, simplicity first and surgical changes.
xllm AGENTS.md
AGENTS.md instructions for xLLM-AI/xllm, covering xllm coding agent instructions, directory structure, code style guide and review instructions.
flashinfer AGENTS.md
Instructions for flashinfer-ai/flashinfer: This repository’s agent instructions live in CLAUDE.md.