methodology

methodology is a skill for Claude Code from melodic-software/claude-code-plugins. It costs 144 tokens per session (1,105 once invoked), scanned A, original, MIT.

A reference guide for evaluating applications that use large language models, such as chatbots or coding agents. It covers measurable goals, test-case design, and methods for grading model responses.

In plain words
What is it for?
It can answer questions about success criteria, evaluation-suite structure, test coverage, and model or human grading.
Why use it?
It helps developers decide what “working well” means and build repeatable checks instead of judging AI output only by intuition.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions Claude Code.

Part of the evals plugin — 2 skills shipped together

Install

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.

agentmods
npx agentmods add skills/melodic-software/claude-code-plugins/methodology
Any agent
npx skills add melodic-software/claude-code-plugins --skill methodology
Clone the repo
git clone --depth 1 https://github.com/melodic-software/claude-code-plugins

Made for: Claude Code.

Or install evals, the plugin that ships this one along with the rest of its 2 skills.

Wrote 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.

agentmods badge for methodology

README.md
[![agentmods](https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/methodology.svg)](https://agentmods.dev/skills/melodic-software/claude-code-plugins/methodology)
Your own site
<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/methodology"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/methodology.svg" alt="Measured on agentmods" height="20"></a>
Per session 144 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,105 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00144 $0.01105
Opus 5 $0.00072 $0.00553
Sonnet 5 $0.00029 $0.00221
Haiku 4.5 $0.00014 $0.00111

Measured 2d ago against content hash 2ef7118889b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

methodology 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.

plugins/evals/skills/methodology/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM evaluation methodology

Distilled from a cover-to-cover reading of Anthropic's "Define success criteria and build evaluations" (https://platform.claude.com/docs/en/test-and-evaluate/develop-tests) and its linked evals cookbook (anthropics/claude-cookbooks misc/building_evals.ipynb), fetched 2026-08-08. Reference files carry per-file source stamps; re-fetch the source page for runnable code or when a specific must be current.

Routing table

Query about... Load
Success criteria: specific/measurable/achievable/relevant, quantifying hazy qualities (safety, empathy), metric menu (F1, BLEU, accuracy, latency, price), criteria dimensions, multidimensional targets success-criteria.md
Eval anatomy (input/output/golden answer/score), golden-answer-as-rubric, design principles, edge-case taxonomy, real-distribution mirroring, volume over polish, authoring vs grading cost asymmetry, generating cases with Claude eval-design.md
Grading ladder (code > LLM > human), LLM-grader rubrics, constrained verdicts, reasoning-then-discard, grader-output validation, different-model grading, testing the grader first grading.md
Concrete recipes: exact match, cosine similarity/consistency, ROUGE-L/summarization, Likert/tone, binary/privacy-leak, ordinal/context utilization recipes.md

Load the most relevant file first; a second only if the first doesn't fully answer.

Quick decision guide (no file load needed):

  • "Where do I start?" → Define measurable success criteria first; evals test against them; only then iterate on prompts.
  • "Is this criterion good?" → It names a specific quality, a number or defined scale, a realistic target, and ties to a user need. "Good performance" fails all four.
  • "Which grading method?" → The fastest, most reliable, most scalable that fits: code-based if the output can be constrained to allow it; LLM-graded for judgment; human only as a last resort.
  • "Can I automate this seemingly subjective eval?" → Usually — constrain the output format, reformat to multiple choice, or use an LLM grader with a tight rubric and constrained verdict.
  • "How many cases?" → Prefer volume with automated grading over a few hand-graded showpieces; generate more from a baseline set with Claude, human-reviewed.
  • "Can I trust my LLM grader?" → Only after reading samples of its verdicts against your own judgment; and grade with a different model than the one that generated the output.
  • "One metric or several?" → Several — most use cases need multidimensional criteria (fidelity + safety + latency + cost); a single headline metric hides regressions.

Read the full file on GitHub · 69 lines

Files

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.

Changes

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.

  1. 2d ago First seen · 69 lines · 144 tokens per session scan A 2ef7118889b9

Subscribe to this mod's changes

methodology is a skill published in the GitHub repository melodic-software/claude-code-plugins (15 stars, last pushed today), licensed MIT. It adds 144 tokens to every session and 1,105 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.