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.
/plugin marketplace add beyondnetcode/evolith_arch32npx agentmods add plugins/beyondnetcode/evolith_arch32/marketplacegit clone --depth 1 https://github.com/beyondnetcode/evolith_arch32Grade A, and why
evolith 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 yesterday.
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": "evolith",
"owner": {
"name": "BeyondNet",
"url": "https://github.com/beyondnetcode"
},
"plugins": [
{
"name": "evolith-governance",
"description": "Executable architecture governance for agents: validate a repository against rulesets, ADRs and SDLC phase gates, and read the verdict together with its coverage. A rule that was not evaluated is reported as UNKNOWN, never as passed.",
"version": "1.3.1",
"source": "./plugins/evolith-governance",
"author": {
"name": "BeyondNet",
"url": "https://github.com/beyondnetcode"
},
"homepage": "https://github.com/beyondnetcode/evolith_arch32#readme",
"repository": "https://github.com/beyondnetcode/evolith_arch32",
"license": "MIT",
"keywords": [
"architecture-governance",
"policy-as-code",
"opa",
"rego",
"adr",
"compliance"
],
"mcpServers": {
"evolith": {
"command": "npx",
"args": ["-y", "@beyondnet/evolith-mcp"]
}
}
}
]
}
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.
- yesterday First seen · 37 lines scan A a64bad81a1cb
evolith is a plugin published in the GitHub repository beyondnetcode/evolith_arch32 (0 stars, last pushed 5d ago), 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 2026-08-31.
Other plugins, from other repositories
aidd-dev
Code transformation: SDLC orchestrator, plan, assert, audit, review, test, refactor, debug, for-sure. Hosts agents.
aidd-vcs
External artifacts: commit, pull-request, release-tag, issue-create.
system-design-skills
A divide-and-conquer wiki of system-design skills. Reason about a design problem one part at a time -- requirements, capacity, APIs, storage, caching, load balancing, messaging, consistency, resilience, delivery, and scaling -- each with generic recipes, cloud-provider variants (AWS/Azure/GCP/Temporal), explicit trade.
aidd-marketplace
Plugin marketplace listing 1 plugin: aidd.
adversarial-review
Gate a staged diff through two independent adversarial reviewers before applying fixes. Bundles the adversarial-reviewer and fixer subagents.
oficina
A lean agent harness for AI-assisted development — NestJS + TypeScript + Prisma + PostgreSQL. Skills for CRUD, Prisma modeling, RBAC, task breakdown and client-facing docs.