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 melodic-software/claude-code-pluginsnpx agentmods add plugins/melodic-software/claude-code-plugins/evalsgit clone --depth 1 https://github.com/melodic-software/claude-code-pluginsWrote 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/melodic-software/claude-code-plugins/evals)<a href="https://agentmods.dev/plugins/melodic-software/claude-code-plugins/evals"><img src="https://agentmods.dev/badge/plugins/melodic-software/claude-code-plugins/evals.svg" alt="Measured on agentmods" height="20"></a>Grade 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 2d 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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "evals",
"version": "0.2.0",
"description": "LLM evaluation methodology and eval-suite design, distilled from Anthropic's official evaluation guidance — a knowledge router over success criteria, eval design, and grading methods (/evals:methodology), plus an action skill that interviews for measurable success criteria and scaffolds a graded eval suite for an LLM app or a Claude Code skill (/evals:design). Guidance and scaffolding only: no command executes model-graded evals.",
"author": {
"name": "Melodic Software",
"email": "[email protected]"
},
"license": "MIT",
"keywords": ["evals", "evaluation", "success-criteria", "llm-judge", "grading", "rubric", "testing", "knowledge", "skill"]
}
What it installs
The manifest is a name and a version. 2 skills travel with it, and installing the plugin installs all of them — 285 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.
- 2d ago First seen · 13 lines scan A 087ec3b46c14
evals is a plugin published in the GitHub repository melodic-software/claude-code-plugins (15 stars, last pushed today), 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
local-llm
Manage local Ollama LLM models for development and testing.
dagster-expert
Comprehensive Dagster development conventions and best practices.
parallel-workflows
Parallel workflow orchestration using git worktrees for concurrent Claude Code sessions.
error-therapist
Audit and rewrite error messages to be helpful and actionable.
content
Content creation and publishing: three writer+optimiser pairs (guides, features, documentation) with research-first workflows, per-content reports, and deterministic audit scoring. Feature writer+optimiser now enforce Technical-Marketing Synthesis (Rule 6: ten sub-checks including coined terminology, dropdown…
crm
CRM and sales pipeline management for systemprompt.io. Tracks leads from first touch through conversion, manages deals and pipeline stages, drafts and sends emails via Resend API (human-approved, never automatic), produces daily sales strategy briefs, and logs every action as a falsifiable hypothesis. Includes…