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 lfyxhappy/lfcode --skill architecture-designergit clone --depth 1 https://github.com/lfyxhappy/lfcodeWrote 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/lfyxhappy/lfcode/architecture-designer)<a href="https://agentmods.dev/skills/lfyxhappy/lfcode/architecture-designer"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/architecture-designer/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/lfyxhappy/lfcode/architecture-designer"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/architecture-designer.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 | $0.00054 | $0.00295 |
| Opus 5 | $0.00027 | $0.00148 |
| Sonnet 5 | $0.00011 | $0.00059 |
| Haiku 4.5 | $0.00005 | $0.00030 |
Grade A, and why
architecture-designer 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 3d 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
Architecture Designer
Design the smallest coherent system change that satisfies the stated outcome and operational constraints.
Workflow
- Map existing entrypoints, components, dependencies, storage, interfaces, failure modes, and deployment boundaries.
- State the functional and non-functional constraints that matter, including latency, availability, privacy, compatibility, ownership, and observability.
- Compare a small number of viable designs against those constraints. Identify data ownership, trust boundaries, API contracts, lifecycle, and failure recovery for each.
- Select or recommend a design with explicit tradeoffs, migration steps, rollback conditions, and compatibility impact.
- Derive implementation slices and verification evidence from the selected design before changing code.
Boundaries
- Do not turn a design request into a broad refactor without evidence that the existing shape cannot meet the requirement.
- Do not claim capacity, security, or reliability properties without measurements, tests, or clearly labeled assumptions.
- Do not implement production changes, create infrastructure, or contact external systems unless the user requests it.
Completion Check
Report the selected design, rejected alternatives, affected boundaries, risks, migration or rollback path, and validation plan.
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.
- 3d ago First seen · 27 lines · 54 tokens per session scan A 8e8713d70408
architecture-designer is a skill published in the GitHub repository lfyxhappy/lfcode (2 stars, last pushed 6d ago), licensed MIT. It adds 54 tokens to every session and 295 once invoked, about $0.0003 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 2026-09-05.
Other skills, from other repositories
telegram
Owner-only Telegram text bridge and Mini App gateway for the existing Ouroboros interface.
mandu-mcp-create-flow
A specification-first workflow for creating features, resources, routes, or API endpoints. It creates a contract describing the expected structure before generating the code, then verifies the result.
mandu-security
Security best practices for Mandu applications. Use when implementing authentication, authorization, input validation, or protecting against common vulnerabilities. Triggers on guard, auth, CSRF, XSS, or security tasks.
mandu-slot
Mandu Slot API for writing business logic. Use when creating API handlers, implementing authentication guards, adding lifecycle hooks, or working with request/response context. Triggers on tasks involving Mandu.filling(), ctx.ok(), ctx.error(), .guard(), .get(), .post(), or slot files.
mandu-fs-routes
File-system based routing for Mandu. Use when creating pages, API routes, layouts, or dynamic routes. Triggers on tasks involving app/ folder, page.tsx, route.ts, layout.tsx, [id], [...slug], or URL patterns.
posthog
Complete guide for the PostHog plugin — REST API access for querying analytics with HogQL, managing feature flags, inspecting events and persons, reading insights, experiments, cohorts, surveys, and more.