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 bengous/claude-code-plugins --skill system-architecturegit clone --depth 1 https://github.com/bengous/claude-code-pluginsWrote 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/bengous/claude-code-plugins/system-architecture)<a href="https://agentmods.dev/skills/bengous/claude-code-plugins/system-architecture"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/system-architecture/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/bengous/claude-code-plugins/system-architecture"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/system-architecture.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 | $0.00047 | $0.01771 |
| Opus 5 | $0.00023 | $0.00886 |
| Sonnet 5 | $0.00009 | $0.00354 |
| Haiku 4.5 | $0.00005 | $0.00177 |
Grade A, and why
system-architecture 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 9d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill guides creation of system architectures that match actual requirements, not imagined future needs. Design real structures with clear boundaries, explicit trade-offs, and appropriate complexity.
The user provides architecture requirements: a system to design, a scaling challenge, or structural decisions to make. They may include context about team size, expected load, or existing constraints.
<architecture_design_thinking>
Design Thinking
Before designing, understand the actual constraints:
- Scale: What's the real load? 100 users? 10,000? 10 million? Design for 10x current, not 1000x.
- Team: How many developers? Microservices for a 3-person team is organizational overhead, not architecture.
- Lifespan: Prototype? MVP? Long-term product? Temporary systems need temporary solutions.
- Change vectors: What actually varies? Abstract only where you have evidence of variation.
The goal is to solve the problem with the least complexity that allows future adaptation. Every abstraction, every boundary, every pattern has a cost. Pay only for what you need.
Then design systems that are:
- Appropriate to actual scale and team size
- Easy to understand and modify
- Explicit about trade-offs and constraints
- Deletable—components can be removed without archaeology </architecture_design_thinking>
<architecture_guidelines>
Architecture Guidelines
Draw Boundaries at Real Differences
Separate concerns that change for different reasons and at different rates.
<example_good title="Meaningful boundary">
Users and Billing are separate bounded contexts
- Different teams own them
- Different change cadences (users: weekly, billing: quarterly)
- Different compliance requirements
src/ users/ # User management domain models.py services.py api.py billing/ # Billing domain models.py services.py api.py shared/ # Truly shared utilities auth.py </example_good>
<example_bad title="Ceremony without purpose">
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.
- 9d ago First seen · 214 lines · 47 tokens per session scan A 50975b028a59
system-architecture is a skill published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 1,771 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
daily-working
End-to-end pipeline: pull a task from the project's task tracker by ID (Redmine or GitHub Issues today, more addable via a new adapter), sanity-check and impact-assess it against the codebase before touching anything, implement it with the Claude CLI, verify the result in a real browser via the Claude Chrome extension…
work
Dispatch a tracker ticket into an isolated worktree and drive it autonomously to an open pull request, then stop for review. Pass interactive to brainstorm the ticket with a human before planning it, or a sentence of editorial direction as a rider. Use when asked to work a ticket end-to-end.
batch
Dispatch a night's batch of Todo tickets — one worktree and one pull request each — and leave a morning summary. Run explicitly; never inferred.
cleanup
Clean up after a merged pull request — return to the base branch, remove the worktree, delete the branch, sweep other stale branches and worktrees, and report tracker state. Use after a merge or whenever asked what is left over.
merge
Merge the reviewed pull request for the current branch, then hand straight off to cleanup. A sentence of editorial direction alongside the green light is read as a rider. Use when a human green-lights an open PR.
prep
Spec a ticket before it is dispatched. Brainstorms it, decides everything it can recommend an answer for, asks a present human about the little that survives, and leaves the spec, the decisions and anything still open as one ticket comment. No worktree, no branch, no pull request, and the ticket stays where it was.