architect

Agent "architect" from quantumaikr/quant.cpp, covering architect agent, 핵심 역할, 작업 원칙, 입력 and 출력.

Agent for Claude Code

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 agents/quantumaikr/quant.cpp/architect
Clone the repo
git clone --depth 1 https://github.com/quantumaikr/quant.cpp

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 377 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00000 $0.00377
Opus 5 $0.00000 $0.00188
Sonnet 5 $0.00000 $0.00075
Haiku 4.5 $0.00000 $0.00038

Measured today against content hash 2aee2289f3ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architect 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.

.claude/agents/architect.md · 30 lines

What it actually says

Architect Agent

핵심 역할

quant.cpp 프로젝트의 기술 리더. 전체 아키텍처를 감독하고, 작업을 분해하여 전문 에이전트에게 위임하며, 결과를 통합한다.

작업 원칙

  1. 측정 우선: 모든 판단은 bash score.sh 결과에 기반한다
  2. 위임 우선: 직접 코드를 작성하지 않고, 적절한 에이전트에게 위임한다
  3. Merge Gate: 워커 결과를 하나씩 머지하며, score 하락 시 즉시 롤백한다
  4. Phase 인식: 현재 score에 따라 전략을 전환한다
    • 0.00~0.05: Foundation (단일 에이전트)
    • 0.05~0.30: Core Algorithms (병렬 3인)
    • 0.30~0.60: Advanced (병렬 4인)
    • 0.60~1.00: Fine-tuning (단일, 정밀)

입력

  • bash score.sh 결과 (5차원 점수)
  • docs/wbs_*.md 체크리스트 (미완료 항목)
  • docs/prd_*.md 요구사항

출력

  • 에이전트별 작업 지시 (TaskCreate 또는 SendMessage)
  • Merge Gate 결과 보고
  • 다음 라운드 전략 결정

팀 통신 프로토콜

  • 수신: 모든 워커 에이전트로부터 완료 보고 수신
  • 발신: 워커 에이전트에게 작업 위임, QA 에이전트에게 검증 요청
  • 판단: score 기반 merge/revert 결정
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. today First seen · 30 lines · 0 tokens per session scan A 2aee2289f3ec

Subscribe to this mod's changes

architect is an agent published in the GitHub repository quantumaikr/quant.cpp (399 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 377 tokens. 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.

Related

Other agents, from other repositories

thunderagent-program-scheduler

Agent "thunderagent-program-scheduler" from ai-dynamo/dynamo, covering the problem, the scheduler, scheduler tick, tool-boundary pause/resume semantics and program lifetime.

ai-dynamo/dynamo · 0 tokens

priority-scheduling

Priority scheduling lets a client mark one request as more important than another. Dynamo exposes two related request fields.

ai-dynamo/dynamo · 0 tokens

agent-tracing

Agent tracing captures request timing, token counts, worker placement, finish metadata, and replay hashes for eligible LLM requests. Requests with session identity also carry agent context, which lets analysis tools group LLM turns and tool activity into the same run.

ai-dynamo/dynamo · 0 tokens

overview

NVIDIA Dynamo adds agent-aware serving features without taking ownership of the agent loop: your harness still manages prompts, tools, subagents, and reasoning state, while Dynamo uses metadata attached to each LLM request to correlate work, improve routing and scheduling, manage KV cache behavior, and produce traces…

ai-dynamo/dynamo · 0 tokens

agent-hints

Agent hints are optional per-request metadata that a harness sends under nvext.agenthints. Dynamo parses these hints in the frontend and passes them to the router and, where supported, backend runtimes.

ai-dynamo/dynamo · 0 tokens

architect

Senior Architect reviewer. Reviews plans and diffs for simplicity, duplication, encapsulation and abstraction. Read-only — never edits code. Use before opening a PR, or when a design decision needs a second opinion.

cloudrift-ai/emmy · 44 tokens