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 Jujitae/invaranpx agentmods add plugins/jujitae/invara/marketplacegit clone --depth 1 https://github.com/Jujitae/invaraGrade A, and why
invara 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
{
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
"name": "invara",
"description": "INVARA - independent verification for AI-built software",
"owner": {
"name": "MIGARYOS"
},
"plugins": [
{
"name": "invara",
"description": "Verify that a change kept the constraints it declared. Verdicts come from file digests and exit codes, never from a model.",
"author": {
"name": "MIGARYOS"
},
"category": "security",
"source": "./plugin",
"homepage": "https://migaryos.com/invara/"
}
]
}
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 · 21 lines scan A 77c0943b0d7b
invara is a plugin published in the GitHub repository Jujitae/invara (0 stars, last pushed 2d ago), licensed Apache-2.0. 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
codspeed
CodSpeed plugin for Claude Code helping with performance measurement and optimization.
codeflow-coding-agent-bundle
Repo-owned Codeflow starter bundle for Claude Code, Codex, and compatible coding-agent installs.
argot
The argot marketplace — the argot voice guardrail as a Claude Code plugin (setup, refresh, check, review-pr, setup-ci, write-rule, and suggest-rules skills, plus the argot MCP server).
argot
A guardrail that flags code foreign to a repo's own patterns — learned from git history. Bundles the argot-setup, argot-refresh, argot-check, argot-review-pr, argot-setup-ci, argot-write-rule, and argot-suggest-rules skills, the argot MCP server, and an opt-in, non-blocking pre-write guardrail hook.
compose-doctor
Plugin marketplace listing 1 plugin: compose-doctor.
nullius
Plugin marketplace listing 1 plugin: nullius.