evaluation-methodology

evaluation-methodology is a skill for Claude Code, Codex from RudyCity/superagent. It costs 77 tokens per session (5,444 once invoked), scanned A, original, MIT.

A quality-assessment method for coding-agent skills and plugins. It defines what to measure, how to score it, and how to interpret strengths, weaknesses, and common problems.

In plain words
What is it for?
Use it to evaluate skills, understand low scores, improve triggering accuracy, and review how well a skill guides an agent through a task.
Why use it?
It gives maintainers a consistent way to judge whether a skill is clear, complete, discoverable, and suitable for agent workflows. This makes improvement priorities easier to identify.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents).

Good fit Use it to evaluate skills, understand low scores, improve triggering accuracy, and review how well a skill guides an agent through a task.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rudycity/superagent/evaluation-methodology
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.

Any agent
npx skills add RudyCity/superagent --skill evaluation-methodology
Clone the repo
git clone --depth 1 https://github.com/RudyCity/superagent

Made for: Claude Code, Codex.

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 evaluation-methodology

README.md
[![agentmods](https://agentmods.dev/badge/skills/rudycity/superagent/evaluation-methodology.svg)](https://agentmods.dev/skills/rudycity/superagent/evaluation-methodology)
Your own site
<a href="https://agentmods.dev/skills/rudycity/superagent/evaluation-methodology"><img src="https://agentmods.dev/badge/skills/rudycity/superagent/evaluation-methodology.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,444 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 213
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
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 $0.00077 $0.05444
Opus 5 $0.00039 $0.02722
Sonnet 5 $0.00015 $0.01089
Haiku 4.5 $0.00008 $0.00544

Measured 4d ago against content hash 1fe24ef30536, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

evaluation-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 4d 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.

.agents/skills/evaluation-methodology/SKILL.md · 551 lines

How it starts

The opening of the file, as written. The whole thing — 551 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluation Methodology

This document is the authoritative reference for how PluginEval measures plugin and skill quality. It covers the three evaluation layers, all ten scoring dimensions, the composite formula, badge thresholds, anti-pattern flags, Elo ranking, and actionable improvement tips.

Related: Full rubric anchors


The Three Evaluation Layers

PluginEval stacks three complementary layers. Each layer produces a score between 0.0 and 1.0 for each applicable dimension, and later layers override or blend with earlier ones according to per-dimension blend weights.

Layer 1 — Static Analysis

Speed: < 2 seconds. No LLM calls. Deterministic.

The static analyzer (layers/static.py) runs six sub-checks directly against the parsed SKILL.md:

Sub-check What it measures
frontmatter_quality Name presence, description length, trigger-phrase quality
orchestration_wiring Output/input documentation, code block count, orchestrator anti-pattern
progressive_disclosure Line count vs. sweet-spot (200–600 lines), references/ and assets/ bonuses
structural_completeness Heading density, code blocks, examples section, troubleshooting section
token_efficiency MUST/NEVER/ALWAYS density, duplicate-line repetition ratio
ecosystem_coherence Cross-references to other skills/agents, "related"/"see also" mentions

These six sub-checks feed directly into six of the ten final dimensions (via STATIC_TO_DIMENSION mapping). The remaining four dimensions — output_quality, scope_calibration, robustness, and part of triggering_accuracy — receive no static contribution and rely entirely on Layer 2 and/or Layer 3.

Anti-pattern penalty is applied multiplicatively to the Layer 1 score:

penalty = max(0.5, 1.0 − 0.05 × anti_pattern_count)

Each additional detected anti-pattern reduces the score by 5%, flooring at 50%.

Layer 2 — LLM Judge

Speed: 30–90 seconds. One or more LLM calls (Sonnet by default). Non-deterministic.

Read the full file on GitHub · 551 lines

Files

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.

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. 4d ago First seen · 551 lines · 77 tokens per session scan A 1fe24ef30536

Subscribe to this mod's changes

evaluation-methodology is a skill published in the GitHub repository RudyCity/superagent (21 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 5,444 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens