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 skills add LegalQuants/LQ-Architect --skill architectgit 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/skills/legalquants/lq-architect/architect)<a href="https://agentmods.dev/skills/legalquants/lq-architect/architect"><img src="https://agentmods.dev/badge/skills/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/skills/legalquants/lq-architect/architect"><img src="https://agentmods.dev/badge/skills/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 | $0.00120 | $0.00825 |
| Opus 5 | $0.00060 | $0.00413 |
| Sonnet 5 | $0.00024 | $0.00165 |
| Haiku 4.5 | $0.00012 | $0.00082 |
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.
How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/architect — build with the sponsor hands-on, leave a net behind
The full discipline lives in method/ARCHITECT-METHOD.md — this file is the mechanics.
The machinery
| Mechanism | Where | What it enforces |
|---|---|---|
| Sign-off records | <project>/signoffs/gate{1,2,3}.md, written/committed by the SPONSOR |
gate order; the Stop hook blocks a netted project lacking gate2 (or the waiver) |
| The waiver | signoffs/waiver.md where the sponsor writes "vibe coded bullshit" |
their written quick-and-dirty consent; tag the build log |
| The net | tests/NET.json + tests/run_all.py (scaffold: python3 net/net_scaffold.py <project>) |
born at Gate 2; the Stop hook blocks turn-end while stale; fingerprint = source + declared external prompts/skills/configs + model id |
| The ratchet | baseline keys in NET.json |
any score below baseline fails; only tests/bless.py --yes from the sponsor's terminal moves them |
| Coverage nudge | the Stop hook, once per session | code directories with no net get named, with a recommendation |
The flow
- Gate 1 — requirements. Interview the sponsor (four categories: must do / must not
do / must cost / must prove; experience words are signals to dig, not requirements).
Deliver the translation table + feasibility verdict. Sponsor writes
signoffs/gate1.md. No design before it. - Eval spike. Tests and eval assets only. Scaffold the net; co-author the golden
dataset (the sponsor's edge cases, their thresholds, set before the build); declare the
project's prompt/skill/config dependencies in NET.json
fingerprint.externalso later edits to them re-arm the net. - Gate 2 — design + checks. Decomposition, pattern + rejected alternative, tradeoff
choices (gain / give up / reversal cost — the sponsor picks), SLA traced to sources,
phase plan. Freeze
BUILD_PLAN.md(template inmethod/). Sponsor writessignoffs/gate2.md. No production code before it. - Build. Phase by phase, each ending
tests/run_all.pygreen + a dated build-log entry. Never edit thresholds/baselines; never re-decide a Gate-2 tradeoff — escalate. Any prompt change updates the eval set in the same change. - Gate 3 — verification. Full net with
--llm; results presented honestly; governance table + handoff package (decision log, rejected alternatives, runbook). Sponsor writessignoffs/gate3.md. Until then: "built, awaiting your verification pass" — never "done".
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.
- 12d ago First seen · 48 lines · 120 tokens per session scan A 22f790a3b2bb
architect is a skill published in the GitHub repository LegalQuants/LQ-Architect (12 stars, last pushed 1mo ago), licensed MIT. It adds 120 tokens to every session and 825 once invoked, about $0.0006 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…