Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add melodic-software/claude-code-plugins/plugin install evalsWrote 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/skills/melodic-software/claude-code-plugins/design)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/design"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/design/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/skills/melodic-software/claude-code-plugins/design"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00181 | $0.04196 |
| Opus 5.5 | $0.00072 | $0.01678 |
| Sonnet 5.5 | $0.00036 | $0.00839 |
| Haiku 4.5 | $0.00018 | $0.00420 |
Grade A, and why
design 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design an evaluation suite
Guides the consumer from "I want to evaluate X" to committed artifacts: a success-criteria document
and a graded eval suite. Method follows Anthropic's official evaluation guidance. This page and
the /evals:methodology page state the rules; work from them. The methodology reference files
linked below are background for a human reader.
Arguments
$ARGUMENTS names the target. Three shapes:
app(or a path/description of an LLM-powered feature): evals for the consumer's own LLM-based application behavior.skill <name>: evals for a consumer-authored Claude Code skill, emitted asevals/evals.jsonnext to that skill.plugin <path>: behavioral cases for a whole Claude Code plugin, measured against a no-plugin baseline. This target is not scaffolded here: hand it toclaude plugin eval init, which interviews for the cases and graders and writes them in the layout its own runner reads. Phase 1 still applies, because criteria come before cases whoever writes them. Before the hand-off, say in one line: read and approve every case input before it is written, and keep raw transcripts out of the cases under Transcripts.
No argument → ask which target, with one example of each.
Route by repository kind
Decide the kind from the repository before Phase 1, then name the route:
| Repository | Route |
|---|---|
| A Claude API app (its code calls Claude through the Anthropic SDK or API) | The first step is /claude-api build-eval, which the user types; this skill never starts it. Lead the answer with it, do not run the phases below by hand before it, and stop. The app target below is for an LLM app that does not call Claude, or for when /claude-api does not resolve |
A skill or plugin repository (a .claude-plugin/plugin.json or SKILL.md files) |
Continue here with the skill or plugin target; /evals:plugin-eval runs a plugin suite |
| Both | Report both routes, each for its own part of the repository |
| No model in the loop | Say that LLM eval design does not apply, and stop |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago Changed · +11 lines 080000f4a77e
- 19d ago Changed · +121 lines · +25 tokens per session 2ab36a5af228
- 21d ago Changed · +12 lines 94b9cfb284e5
- 1mo ago Changed · +11 lines · +16 tokens per session 7e38a0daaaf6
- 1mo ago Changed · -1 tokens per session a9b4e1b49d1e
- 1mo ago Changed · +4 lines 3eec68579525
- 1mo ago Changed · +3 lines 05ee9de55730
- 1mo ago First seen · 101 lines · 141 tokens per session scan A c2335454dd84
design is a skill published in the GitHub repository melodic-software/claude-code-plugins (26 stars, last pushed today), licensed MIT. It adds 181 tokens to every session and 4,196 once invoked, about $0.0007 per session on Opus 5.5. 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 skills, from other repositories
benchmark-before-optimize
For performance work: measure before changing, profile to find bottlenecks, compare before and after.
parse-extract-input
For text processing: extract numbers, words, structured data from messy text using regex patterns, parsing utilities.
test-structural-invariants
For data structure validation: test lengths, relationships, constraints that must hold, verify setup is correct.
test-with-examples
For example-driven development: test cases as specifications, input/output pairs, documentation through examples.
verify-solution-properties
For solution checking: independent verification that result is correct, separate from how it was computed.
verify-with-inline-tests
For test co-location: tests in same file as code, run with main, tests as documentation and examples.