system-design

system-design is a skill for Claude Code, Codex from pinchen147/system-design-skill. It costs 174 tokens per session (3,712 once invoked), scanned C, original, MIT.

A production-system design process for choosing or changing software architecture using repository evidence, workload estimates, correctness rules, failure cases, and operating limits. It compares genuinely different designs and leaves a design record for later coding sessions.

In plain words
What is it for?
Use it to size a system, identify protected behavior and failure modes, compare production-ready architecture options, recommend one with supporting evidence, and document the result.
Why use it?
It replaces intuition-led architecture decisions with explicit evidence and trade-offs. This helps avoid systems that fail under expected load or designs that are more complicated than the requirements justify.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: reads .claude/ paths; mentions subagents.

Part of the system-design-skill plugin — 1 skill shipped together

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.

agentmods
npx agentmods add skills/pinchen147/system-design-skill/system-design
Any agent
npx skills add pinchen147/system-design-skill --skill system-design
Clone the repo
git clone --depth 1 https://github.com/pinchen147/system-design-skill

Made for: Claude Code, Codex.

Or install system-design-skill, the plugin that ships this one along with the rest of its 1 skill.

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 system-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/pinchen147/system-design-skill/system-design.svg)](https://agentmods.dev/skills/pinchen147/system-design-skill/system-design)
Your own site
<a href="https://agentmods.dev/skills/pinchen147/system-design-skill/system-design"><img src="https://agentmods.dev/badge/skills/pinchen147/system-design-skill/system-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 174 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,712 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
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 $0.00174 $0.03712
Opus 5 $0.00087 $0.01856
Sonnet 5 $0.00035 $0.00742
Haiku 4.5 $0.00017 $0.00371

Measured 6d ago against content hash a5a0e9eb2bf8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

system-design scanned grade C with 2 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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/render_report.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

If the skill directory is not known, find it rather than skipping the step: `ls ~/.claude/skills/system-design/scripts/render_report.py ~/.agents/skills/system-design/scripts/render_report.py 2>/dev/null` covers both sta

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

If the skill directory is not known, find it rather than skipping the step: `ls ~/.claude/skills/system-design/scripts/render_report.py ~/.agents/skills/system-design/scripts/render_report.py 2>/dev/null` covers both sta
skills/system-design/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

System Design

Architecture is decided by invariants, workload numbers, failure modes, and operating constraints—not vibes. Draw the simplest production-viable candidate first, add only evidence-surviving alternatives that differ on a load-bearing axis, recommend one with an evidence chain, and leave a design artifact another coding-agent session can continue.

The process is identical in repository and greenfield work; interview-grade reasoning falls out of production discipline.

Every recommendation must cite an envelope number, a correctness invariant, a named failure mode, or a principle from HEURISTICS.md.

Do not load examples by default. Only if a first-draft recommendation or interface remains generic, consult the matching BAD/GOOD contrast in EXAMPLES.md, then replace generic language with the relevant number, invariant, ownership boundary, or failure behavior.

Process

0. Size the ask before running the process

This process earns its cost when a decision is hard to reverse, the numbers are load-bearing, or several structurally different designs are genuinely live. Sketch the envelope first. If it lands below the anti-overengineering gates in HEURISTICS.md, or one recorded decision already forces the answer, say which gate or decision closed it and answer directly in a paragraph—no artifacts. A false choice rendered as peer tabs is worse than no document.

When the process does run, draw the simplest production-viable design first. Add a candidate only when it remains viable after the envelope and invariants and changes a load-bearing axis—for example, the measured scale boundary or the dominant correctness, failure-isolation, cost, or operability risk. Record options closed by a requirement, gate, or named failure as one-line rejections; do not draw, rate, or audit them as peers. Three candidates is the ceiling, not a target.

1. Locate and resume

List existing designs—docs/design/*/design.json, or ./*/design.json outside a git repo—and read each one's slug, title, and status. If one covers this ask, load it and apply the user's feedback before doing new discovery; if two could, name both and ask which.

Read the full file on GitHub · 154 lines

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. 6d ago First seen · 154 lines · 174 tokens per session scan C a5a0e9eb2bf8

Subscribe to this mod's changes

system-design is a skill published in the GitHub repository pinchen147/system-design-skill (22 stars, last pushed 25d ago), licensed MIT. It adds 174 tokens to every session and 3,712 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

distributed-feasibility-checker

Evaluate whether a system should adopt distributed architecture by systematically checking against the 8 Fallacies of Distributed Computing and assessing team/operational readiness. Use this skill whenever the user is considering microservices, debating monolith vs distributed, hearing "let's use microservices,"…

bookforge-ai/bookforge-skills · 86 tokens

software-architect

Software architecture engineering consultancy skill. Analyzes overall application structure, recommends sustainable approaches, enforces architectural consistency, and documents decisions for future sessions. Use this skill whenever the user asks about system design, architecture decisions, feature integration…

eligapris/software-architect · 171 tokens

data-charts-tako

Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.

gooseworks-ai/goose-skills · 35 tokens

apollo-lead-finder

Two-phase Apollo.io prospecting: free People Search to discover ICP-matching leads, then selective enrichment to reveal emails/phones (credits per contact). Creates Apollo lists. Deduplicates against existing contacts by LinkedIn URL.

gooseworks-ai/goose-skills · 51 tokens

nw-fp-clojure

Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.

nWave-ai/nWave · 25 tokens

monorepo-management

Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.

wshobson/agents · 54 tokens