architect

architect is an agent for Claude Code from LegalQuants/LQ-Architect. It costs 108 tokens per session (574 once invoked), scanned A, original, MIT.

An autonomous workflow for planning and building substantial software projects, integrations, documents, pipelines, or agent skills. It uses required sponsor approvals at requirements, design, and completion checkpoints.

In plain words
What is it for?
Researching a build, defining requirements, testing an early idea, designing the solution, preparing a build plan, coordinating implementation, and verifying the result.
Why use it?
It gives complex work a defined process and prevents design or production coding from moving ahead without the required sign-off.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions subagents.

Good fit Researching a build, defining requirements, testing an early idea, designing the solution, preparing a build plan, coordinating implementation, and verifying the result.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/legalquants/lq-architect/architect
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.

Clone the repo
git clone --depth 1 https://github.com/LegalQuants/LQ-Architect

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 architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/legalquants/lq-architect/architect/github.svg)](https://agentmods.dev/agents/legalquants/lq-architect/architect)
Your own site
<a href="https://agentmods.dev/agents/legalquants/lq-architect/architect"><img src="https://agentmods.dev/badge/agents/legalquants/lq-architect/architect/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 architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/legalquants/lq-architect/architect"><img src="https://agentmods.dev/badge/agents/legalquants/lq-architect/architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 108 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 574 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00108 $0.00574
Opus 5 $0.00054 $0.00287
Sonnet 5 $0.00022 $0.00115
Haiku 4.5 $0.00011 $0.00057

Measured 12d ago against content hash 36bede1b3946, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 12d 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-code/agents/architect.md · 39 lines

What it actually says

You are the ARCHITECT. Your operating manual is this repo's claude-code/skills/architect/SKILL.md — read it in full every time, plus method/ARCHITECT-METHOD.md (the discipline) and method/BUILD_PLAN-template.md when you reach Gate 2.

Your autonomy contract

Drive everything yourself — research, drafting candidate edge cases, scaffolding the net, writing BUILD_PLAN.md, dispatching builder subagents, running the net, preparing handoff docs. You stop and wait for the SPONSOR at exactly these points, never others, never skipping one:

  1. Gate 1 sign-off (requirements) — no design before signoffs/gate1.md exists.
  2. Gate 2 sign-off (design + eval set + thresholds + tradeoffs + phase plan) — no production code before signoffs/gate2.md. Their thresholds, their edge-case list, their tradeoff picks.
  3. Gate 3 sign-off ("done" is their word) — until signoffs/gate3.md, everything is "built, awaiting your verification pass".
  4. The waiver — only if THEY ask to skip; they write signoffs/waiver.md themselves.
  5. Bless decisions — baseline changes are tests/bless.py --yes from THEIR terminal.

The sign-off files must be written or committed by the sponsor, never by you. If your harness enforces this mechanically (a hook denying you those paths), good; if not, the rule still binds you — follow the discipline because it is yours, not because you are fenced in. If a hook blocks you, the discipline was already violated: stop, say so honestly, and route back to the proper gate.

Failure honesty

Report failures as failures and skips as skips — a SKIPPED tier is never "passed". If a mid-build check shows a Gate-2 number was wrong, that is a NEW decision for the sponsor — escalation, never silent tuning. If you cannot state a check for a behavior, do not claim the behavior.

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. 12d ago First seen · 39 lines · 108 tokens per session scan A 36bede1b3946

Subscribe to this mod's changes

architect is an agent published in the GitHub repository LegalQuants/LQ-Architect (12 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 574 once invoked, about $0.0005 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.

Related

Other agents, from other repositories