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.
npx agentmods add skills/melodic-software/claude-code-plugins/designnpx skills add melodic-software/claude-code-plugins --skill designgit 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/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.svg" alt="Measured on agentmods" 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 | $0.00141 | $0.01407 |
| Opus 5 | $0.00071 | $0.00704 |
| Sonnet 5 | $0.00028 | $0.00281 |
| Haiku 4.5 | $0.00014 | $0.00141 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 104 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 — load
/evals:methodology reference files as each phase needs them (they carry the distilled source).
Arguments
$ARGUMENTS names the target. Two 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.
No argument → ask which target, with one example of each.
Phase 1 — success criteria (before any cases)
Interview until each criterion is specific, measurable, achievable, relevant (success-criteria.md):
- What does success look like, concretely? Reject unmeasurable phrasings by proposing a measurable rewrite ("good answers" → "≥90% of answers judged correct against their rubric").
- Which dimensions matter? Walk the eight (fidelity, consistency, relevance/coherence, tone/style, privacy, context use, latency, price); keep the ones with a real user need. Most targets are multidimensional — press for at least fidelity plus one guardrail dimension.
- What is achievable? Anchor each target to a baseline (current behavior, prior experiment, or a published benchmark); when no baseline exists, record the first run AS the baseline.
Write the result to docs/eval-criteria/<target>.md in the consumer repo (create the directory if
absent; respect an existing consumer convention for criteria docs if one is documented in the
consumer's own CLAUDE.md or rules). Each criterion: dimension, metric, target number/scale,
rationale line.
Phase 2 — eval suite
Per criterion, pick the cheapest reliable grading method (grading.md, recipes.md): code-graded where the output can be constrained to allow it; LLM-graded with a tight rubric and constrained verdict otherwise; human grading only with stated justification.
What ships with it
1 file 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.
- today Changed · +3 lines 05ee9de55730
- 2d 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 (15 stars, last pushed today), licensed MIT. It adds 141 tokens to every session and 1,407 once invoked, about $0.0007 per session on Opus 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
parse-extract-input
For text processing: extract numbers, words, structured data from messy text using regex patterns, parsing utilities.
local-llm
Manage local Ollama LLM models for development and testing. Use when: running local models, configuring Ollama, switching between fast/quality models, optimizing VRAM usage, troubleshooting model performance, creating Modelfiles, or integrating local LLMs with applications via OpenAI-compatible API. Triggers: ollama…
dagster-expert
Expert guidance for working with Dagster and the dg CLI. ALWAYS use before doing any task that requires knowledge specific to Dagster, or that references assets, materialization, components, data tools or data pipelines. Common tasks may include creating a new project, adding new definitions, understanding the current…
ai-policy-generator
AI governance policy creation for nonprofits and enterprises with frameworks, risk assessment, ethical guidelines, and compliance templates. Use when drafting AI usage policies, responsible AI frameworks, or organizational AI governance documents.
data-engineering
ETL/ELT pipelines, data warehousing (BigQuery, Snowflake, Redshift), stream processing (Kafka, Spark Streaming), orchestration (Airflow, Dagster, Prefect), dbt transformations, and data lake architecture. Use when building data pipelines, designing warehouse schemas, or implementing real-time data processing.
llm-evaluation
LLM evaluation and testing patterns including prompt testing, hallucination detection, benchmark creation, and quality metrics. Use when testing LLM applications, validating prompt quality, implementing systematic evaluation, or measuring LLM performance.