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 tessaryai/pluginsnpx agentmods add plugins/tessaryai/plugins/evalsgit clone --depth 1 https://github.com/tessaryai/pluginsGrade A, and why
evals 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": "evals",
"description": "Connect your repo to evals.tessary.ai and work with your evals from the coding agent \u2014 wire trace ingestion over OTLP, tag your call sites, assess graders, query failing traces, read the cases and root-cause reports the platform opens, and author per-call-site SOP-conformance files (derive from the code, reconcile on change, lint locally). The platform's observer authors and maintains your eval bundle from there.",
"version": "0.27.1",
"author": {
"name": "Tessary AI"
},
"homepage": "https://evals.tessary.ai",
"repository": "https://github.com/tessaryai/plugins",
"license": "MIT",
"keywords": [
"evals",
"llm",
"graders",
"observability",
"mcp",
"coding-agent"
]
}
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 · 20 lines scan A 0184ab4b1530
evals is a plugin published in the GitHub repository tessaryai/plugins (3 stars, last pushed 14d 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
ghost-font-tools
Tools for decoding motion-hidden text in videos.
ghost-font-decoder
Reveal text hidden in ghost-font videos (motion-defined dot text) using optical flow and OCR.
a11y-audit
Full accessibility audit with WCAG compliance checking.
bevy-plugin
Bevy game engine development - ECS, rendering, game architecture.
ryk
ryk safety hooks and skills for Claude Code.
quick-pr
Split a minor change from the current work into a separate worktree and open a PR without interrupting your flow. Use when an unrelated small fix (typo, lint rule, config tweak) is sitting in a feature branch and the user wants it shipped on its own — \"quick PR\", \"split this out\", \"ship this separately\".…