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 davidYichengWei/Agency --skill system-designgit clone --depth 1 https://github.com/davidYichengWei/AgencyWrote 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/davidyichengwei/agency/system-design)<a href="https://agentmods.dev/skills/davidyichengwei/agency/system-design"><img src="https://agentmods.dev/badge/skills/davidyichengwei/agency/system-design/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/davidyichengwei/agency/system-design"><img src="https://agentmods.dev/badge/skills/davidyichengwei/agency/system-design.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 | $0.00058 | $0.00518 |
| Opus 5 | $0.00029 | $0.00259 |
| Sonnet 5 | $0.00012 | $0.00104 |
| Haiku 4.5 | $0.00006 | $0.00052 |
Grade A, and why
system-design 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 8d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Design
Prerequisite
spec.md sections 1-3 must be complete and approved. If not, invoke requirements-clarification first.
Core Principle
The agent drafts the design, the user reviews it. Research the codebase thoroughly — especially adjacent and similar modules — before proposing anything. The design should follow existing patterns in the codebase unless there's a good reason to deviate, and trade-offs should be explicit.
Workflow
- Use researcher subagent to investigate: existing module structure, adjacent/similar modules' implementation patterns, interfaces, dependencies, constraints
- Draft sections 4.1 (overview), 4.2 (key design decisions), 4.3 (trade-offs) — focusing on WHAT and WHY, not implementation details
- Draft section 5 (alternatives considered)
- Present sections 4-5 at Gate: Solution Design for approval
- After Solution Design approval, draft section 6 (test plan) → present at Gate: Test Plan
- Draft section 7 (observability & operations) if applicable → present at Gate: Ops/Visibility, or mark N/A
Abstraction Level
The design doc captures decisions and trade-offs, not code. Use this as a guide:
| Belongs in spec.md | Belongs in code / tasks.md |
|---|---|
| Module boundaries and dependencies | Specific file changes |
| Interface contracts and data models | Function signatures and implementations |
| Key algorithms (conceptual) | Line-by-line logic |
| Trade-offs and their rationale | Configuration values |
If you're writing function names or line numbers, it's too detailed for the spec.
Common Pitfalls
| Mistake | Do this instead |
|---|---|
| Designing without researching existing patterns | Always investigate how adjacent modules solve similar problems — deviate only with explicit rationale |
| Writing implementation-level detail in the spec | Keep it at the architecture/interface level — implementation goes in tasks.md |
| Proposing a single approach without alternatives | Always consider at least one alternative and explain why you chose your approach |
| Skipping test plan or ops sections | These are quality gates — fill them or explicitly mark N/A with rationale |
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.
- 8d ago First seen · 46 lines · 0 tokens per session scan A 343f7acdbf62
system-design is a skill published in the GitHub repository davidYichengWei/Agency (5 stars, last pushed 4mo ago), licensed MIT. It adds 58 tokens to every session and 518 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 2026-08-31.
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…