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.
git clone --depth 1 https://github.com/levnikolaevich/claude-code-skillsWrote 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/plugins/levnikolaevich/claude-code-skills/architecture-suite)<a href="https://agentmods.dev/plugins/levnikolaevich/claude-code-skills/architecture-suite"><img src="https://agentmods.dev/badge/plugins/levnikolaevich/claude-code-skills/architecture-suite.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
architecture-suite 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 4d 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
{
"name": "architecture-suite",
"description": "Architecture baselines, current-state documentation, target designs, decisions, diagrams, and migration plans.",
"source": "./plugins/architecture-suite",
"strict": false
}What it installs
The manifest is a name and a version. 6 skills travel with it, and installing the plugin installs all of them — 192 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill ln-71-system-design-baseline-builder A 30 tokens
- Skill ln-73-system-design-proposal-builder A 32 tokens
- Skill ln-76-architecture-migration-planner A 34 tokens
- Skill ln-72-current-architecture-documenter A 31 tokens
- Skill ln-74-architecture-decision-recorder A 32 tokens
- Skill ln-75-architecture-diagram-builder A 33 tokens
What ships with it
1 file beside marketplace.json#architecture-suite in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 6 lines scan A a2aa52336dc7
architecture-suite is a plugin published in the GitHub repository levnikolaevich/claude-code-skills (558 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
pr-workflow
PR and issue lifecycle — structured planning (CEO/Eng gates), PR creation, code review, issue triage, session handoffs.
toru-claude-agents
A dev pipeline for Claude Code that will not call work done until tests, lint and a security audit all exit zero. Seven specialists run it, for 1.1k tokens of always-on context.
opencode-power-pack
Fifty-four software-development workflows for Claude Code, Codex, OpenCode, and Pi.
code-quality
Code quality pipeline — SOLID refactoring, TDD workflow, design patterns, performance optimization, and 6 specialist review agents.
open-pr
Pre-flight checks and PR creation workflow: run tests, open a PR, code review, and check CI.
ticket-triage
Backlog-drain loop: rank the open tickets, dispatch the genuinely startable ones in parallel (worktree-isolated, role-briefed, honest width), verify and merge each result, and re-triage on every completion until the queue is empty or everything left needs the user.