eval-coach

eval-coach is a skill for Claude Code from BayramAnnakov/eval-coach. It costs 20 tokens per session (2,843 once invoked), scanned A, original, MIT.

A guided method for evaluating AI applications through Evaluation-Driven Development (EDD), which means defining and testing quality throughout development.

In plain words
What is it for?
It is for defining success measures, creating test cases, choosing automated or human review, adding evaluations to CI/CD, and monitoring production quality.
Why use it?
It helps teams measure reliability, catch regressions, and investigate quality problems instead of relying on intuition.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool; positional $N argument; mentions Claude Code.

Part of the eval-coach plugin — 1 skill shipped together

Good fit It is for defining success measures, creating test cases, choosing automated or…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bayramannakov/eval-coach/eval-coach
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 BayramAnnakov/eval-coach --skill eval-coach
Clone the repo
git clone --depth 1 https://github.com/BayramAnnakov/eval-coach

Made for: Claude Code.

Or install eval-coach, the plugin that ships this one along with the rest of its 1 skill.

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 eval-coach

README.md
[![agentmods](https://agentmods.dev/badge/skills/bayramannakov/eval-coach/eval-coach.svg)](https://agentmods.dev/skills/bayramannakov/eval-coach/eval-coach)
Your own site
<a href="https://agentmods.dev/skills/bayramannakov/eval-coach/eval-coach"><img src="https://agentmods.dev/badge/skills/bayramannakov/eval-coach/eval-coach.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,843 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.
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 $0.00020 $0.02843
Opus 5 $0.00010 $0.01422
Sonnet 5 $0.00004 $0.00569
Haiku 4.5 $0.00002 $0.00284

Measured 6d ago against content hash d60152bd7830, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

eval-coach 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 6d 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.

SKILL.md · 344 lines

How it starts

The opening of the file, as written. The whole thing — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eval Coach

An Agent Skill for designing comprehensive AI evaluation strategies using Evaluation-Driven Development (EDD).

Overview

Eval Coach guides you through a structured 5-step framework for evaluating LLM applications:

  1. Define Success - Map business goals to measurable metrics
  2. Design Dataset - Create diverse test cases (happy path, edge cases, adversarial)
  3. Select Methods - Choose Automated, LLM-as-Judge, or Human evaluation
  4. Plan Automation - Integrate evals into CI/CD
  5. Monitor Production - Track drift and collect feedback

When to Use This Skill

Invoke this skill when:

  • Starting a new AI project and need an evaluation strategy
  • Improving an existing agent's reliability
  • Comparing different implementation approaches
  • Setting up CI/CD for AI products
  • Debugging production quality issues

Evaluation Philosophy

Capability vs Regression Evals

Two fundamentally different types of evaluations:

Type Starting Point Goal When Failure Occurs
Capability Near 0% Push higher over time Expected - iterate and improve
Regression Near 100% Maintain - don't drop Alarming - investigate immediately

Key Insight: Convert production bugs into regression tests. Every bug you fix becomes a test that ensures it never happens again.

pass@k vs pass^k (Handling Non-Determinism)

Agents are probabilistic. Use the right metric:

pass@k = Probability of at least one success in k attempts

  • Formula: 1 - (1-p)^k
  • As k increases, score rises - more "shots on goal" means higher odds of success
  • Use for coding agents where pass@1 matters most (first try counts)
  • Use when multiple solution attempts are acceptable

pass^k = Probability of succeeding every time in k attempts

  • Formula: p^k
  • As k increases, score falls - demanding consistency across more trials is harder
  • Example: 75% per-trial rate × 3 trials = (0.75)³ ≈ 42% pass^3
  • Use for customer-facing agents where users expect reliable behavior every time

Read the full file on GitHub · 344 lines

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. 6d ago First seen · 344 lines · 20 tokens per session scan A d60152bd7830

Subscribe to this mod's changes

eval-coach is a skill published in the GitHub repository BayramAnnakov/eval-coach (4 stars, last pushed 7mo ago), licensed MIT. It adds 20 tokens to every session and 2,843 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

deepeval

DeepEval evaluation workflow for AI agents and LLM applications. TRIGGER when the user wants to evaluate or improve an AI agent, tool-using workflow, multi-turn chatbot, RAG pipeline, or LLM app; add evals; generate datasets or goldens; use deepeval generate; use deepeval test run; send results to Confident AI…

confident-ai/deepeval · 229 tokens

deepeval-otel

Export raw OpenTelemetry traces from an AI application to Confident AI's Observatory. TRIGGER when the user wants to send OpenTelemetry or OTLP traces/spans from an LLM app, agent, RAG pipeline, or chatbot to Confident AI; configure the Confident AI OTLP endpoint; set confident.span. or confident.trace. attributes…

confident-ai/deepeval · 226 tokens

deepeval-tracing

Instrument an AI application with DeepEval's native tracing so its behavior is visible in Confident AI. TRIGGER when the user wants to add DeepEval tracing or @observe to an LLM app, agent, RAG pipeline, or chatbot; wire a framework, model-provider, or vector-database integration (LangGraph, LangChain, OpenAI Agents…

confident-ai/deepeval · 208 tokens

tracely

Instrument AI agents with Tracely and turn their production traces into CI gates. Use when the user mentions Tracely, tracely-ai, tracelysdk, the tracely CLI, or asks to trace/observe an AI agent, add LLM evaluators or LLM-as-a-judge columns, debug why a trace or conversation isn't showing up, wire agent regression…

Jwuthri/Tracely-ai · 120 tokens

LLM Tracing and Observability Setup

Configures end-to-end tracing for an LLM application using OpenTelemetry with LangSmith, Langfuse, or Helicone — span naming, metadata tagging, latency thresholds, and cost tracking.

Notysoty/openagentskills · 48 tokens

llm-evaluation

LLM evaluation — automated metrics, human feedback, benchmarking. Use when testing performance, measuring AI quality, or establishing evaluation frameworks.

martineserios/thebrana · 31 tokens