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/UiPath/coder_evalWrote 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/uipath/coder_eval/coder-eval)<a href="https://agentmods.dev/plugins/uipath/coder_eval/coder-eval"><img src="https://agentmods.dev/badge/plugins/uipath/coder_eval/coder-eval/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/plugins/uipath/coder_eval/coder-eval"><img src="https://agentmods.dev/badge/plugins/uipath/coder_eval/coder-eval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
coder-eval 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 today.
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://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "coder-eval",
"displayName": "Coder Eval",
"version": "0.12.14",
"description": "Test whether your Claude Code skills actually trigger, and benchmark any coding agent — author, run, and analyze the eval suite that proves it, locally or as a CI gate.",
"author": { "name": "UiPath", "email": "[email protected]", "url": "https://github.com/UiPath/coder_eval" },
"homepage": "https://coder-eval.com",
"repository": "https://github.com/UiPath/coder_eval",
"license": "Apache-2.0",
"keywords": [
"claude-code-skills",
"skill-testing",
"skill-activation",
"evaluation",
"benchmark",
"agent-testing",
"github-actions",
"sandbox",
"llm-judge",
"ci"
]
}
What it installs
The manifest is a name and a version. 6 skills travel with it, and installing the plugin installs all of them — 284 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- today Changed 7096d337895a
- 2d ago Changed a4d9bda2ed69
- 9d ago Changed bc7441e053d2
- 10d ago Changed 7dbf4894c81f
- 12d ago Changed c22566fbe19f
- 16d ago Changed 9dce265ef546
- 20d ago Changed ae4ff92011a0
- 22d ago Changed 94a473468d92
- 23d ago Changed 5c2d8ba584fd
- 27d ago First seen · 24 lines scan A 6f4204320ba5
coder-eval is a plugin published in the GitHub repository UiPath/coder_eval (151 stars, last pushed today), 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 2026-08-30.
Other plugins, from other repositories
evalview
Open-source testing and regression detection framework for AI agents. Golden baseline diffing, CI/CD integration, works with LangGraph, CrewAI, OpenAI, Anthropic Claude, HuggingFace, Ollama, and MCP.
ultrasafe
Pre-release / pre-update simulated penetration testing discipline — v0.2.x runtime activation cut (advisory mode; v0.2.1 = ship-surface alignment doc patch). Wraps Ultrasafe.md v0.2.1 substantive spec (3522 lines, +978 since v0.1.0) with the runtime layer: 8 attacker SKILL.md (ultrasafe-ai-llm-redteam · ultrasafe-web.
iris-eval
Stop shipping agents on vibes — agent eval for any MCP workflow. Score output quality, catch PII and prompt injection, verify citations, and enforce cost budgets. Adds the Iris MCP server (12 tools) plus the iris-eval skill that guides eval-driven development.
god-prompt-mcp
GodPrompt engineering workflows for task routing, TDD, debugging, verification, and progressive disclosure.
momentic
Skills for Momentic end-to-end testing. They cover writing browser and mobile app tests, running them, and fixing them when they break, and they connect the local Momentic MCP server.
trial
Pre-delivery evidence gate: withhold unsupported completion claims and release only verified results.