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.
git clone --depth 1 https://github.com/LegalQuants/LQ-ArchitectWrote 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.
[](https://agentmods.dev/agents/legalquants/lq-architect/architect)<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.
<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>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00108 | $0.00574 |
| Opus 5.5 | $0.00043 | $0.00230 |
| Sonnet 5.5 | $0.00022 | $0.00115 |
| Haiku 4.5 | $0.00011 | $0.00057 |
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 2mo 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.
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:
- Gate 1 sign-off (requirements) — no design before
signoffs/gate1.mdexists. - 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. - Gate 3 sign-off ("done" is their word) — until
signoffs/gate3.md, everything is "built, awaiting your verification pass". - The waiver — only if THEY ask to skip; they write
signoffs/waiver.mdthemselves. - Bless decisions — baseline changes are
tests/bless.py --yesfrom 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.
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.
- 2mo ago First seen · 39 lines · 108 tokens per session scan A 36bede1b3946
architect is an agent published in the GitHub repository LegalQuants/LQ-Architect (14 stars, last pushed 3mo ago), licensed MIT. It adds 108 tokens to every session and 574 once invoked, about $0.0004 per session on Opus 5.5. 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.
architect compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| architectLegalQuants/LQ-Architect | Agent | 14 | 3mo ago | MIT | A | 108 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | today | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 3d ago | MIT | A | 52 | Claude Code |
| Pimcore Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 26 | Claude Code |