imlazy-eval

imlazy-eval is a skill for Claude Code from hnikoloski/imlazy. It costs 20 tokens per session (1,644 once invoked), scanned A, a copy of eval-harness, MIT.

A framework for evaluating Claude Code sessions using eval-driven development, a method that defines expected results before implementation and tests them repeatedly. It treats evaluations as tests for AI-assisted work.

In plain words
What is it for?
Defining task success criteria, measuring agent reliability with pass@k, creating regression evaluations, and comparing model or prompt changes.
Why use it?
It replaces vague judgments about whether an agent task worked with stated pass/fail checks and regression tests, which catch failures after changes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the imlazy plugin — 26 skills, 1 command, 1 hook shipped together

Good fit Defining task success criteria, measuring agent reliability with pass@k, creating regression evaluations, and comparing model or prompt changes.

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

Made for: Claude Code.

Or install imlazy, the plugin that ships this one along with the rest of its 26 skills, 1 command, 1 hook.

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 imlazy-eval

README.md
[![agentmods](https://agentmods.dev/badge/skills/hnikoloski/imlazy/imlazy-eval/github.svg)](https://agentmods.dev/skills/hnikoloski/imlazy/imlazy-eval)
Your own site
<a href="https://agentmods.dev/skills/hnikoloski/imlazy/imlazy-eval"><img src="https://agentmods.dev/badge/skills/hnikoloski/imlazy/imlazy-eval/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.

agentmods 80×15 button for imlazy-eval

Your own site · 80×15
<a href="https://agentmods.dev/skills/hnikoloski/imlazy/imlazy-eval"><img src="https://agentmods.dev/badge/skills/hnikoloski/imlazy/imlazy-eval.svg" alt="Reviewed on agentmods" width="80" 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 1,644 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 83% copy Near-identical to another mod 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 $0.01644
Opus 5 $0.00010 $0.00822
Sonnet 5 $0.00004 $0.00329
Haiku 4.5 $0.00002 $0.00164

Measured 10d ago against content hash eb5bc1eede38, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

imlazy-eval 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.

Origin

This is a copy

83% identical to eval-harness — 28 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/imlazy-eval/SKILL.md · 270 lines

How it starts

The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eval Harness Skill

A formal evaluation framework for Claude Code sessions, implementing eval-driven development (EDD) principles.

When to Activate

  • Setting up eval-driven development (EDD) for AI-assisted workflows
  • Defining pass/fail criteria for Claude Code task completion
  • Measuring agent reliability with pass@k metrics
  • Creating regression test suites for prompt or agent changes
  • Benchmarking agent performance across model versions

Philosophy

Eval-Driven Development treats evals as the "unit tests of AI development":

  • Define expected behavior BEFORE implementation
  • Run evals continuously during development
  • Track regressions with each change
  • Use pass@k metrics for reliability measurement

Eval Types

Capability Evals

Test if Claude can do something it couldn't before:

[CAPABILITY EVAL: feature-name]
Task: Description of what Claude should accomplish
Success Criteria:
  - [ ] Criterion 1
  - [ ] Criterion 2
  - [ ] Criterion 3
Expected Output: Description of expected result

Regression Evals

Ensure changes don't break existing functionality:

[REGRESSION EVAL: feature-name]
Baseline: SHA or checkpoint name
Tests:
  - existing-test-1: PASS/FAIL
  - existing-test-2: PASS/FAIL
  - existing-test-3: PASS/FAIL
Result: X/Y passed (previously Y/Y)

Grader Types

1. Code-Based Grader

Deterministic checks using code:

# Check if file contains expected pattern
grep -q "export function handleAuth" src/auth.ts && echo "PASS" || echo "FAIL"

# Check if tests pass
npm test -- --testPathPattern="auth" && echo "PASS" || echo "FAIL"

# Check if build succeeds
npm run build && echo "PASS" || echo "FAIL"

2. Model-Based Grader

Use Claude to evaluate open-ended outputs:

[MODEL GRADER PROMPT]
Evaluate the following code change:
1. Does it solve the stated problem?
2. Is it well-structured?
3. Are edge cases handled?
4. Is error handling appropriate?

Score: 1-5 (1=poor, 5=excellent)
Reasoning: [explanation]

Read the full file on GitHub · 270 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. 10d ago First seen · 270 lines · 20 tokens per session scan A eb5bc1eede38

Subscribe to this mod's changes

imlazy-eval is a skill published in the GitHub repository hnikoloski/imlazy (2 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 1,644 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 83% identical to eval-harness, differing in 28 lines, and is treated as a copy.

Related

Other skills, from other repositories

debug

Debug a stubborn bug with a deterministic reproduction, hypothesis ledger, one-variable fixes, and a regression test. Use after the first obvious look fails, reproduction is unclear, or a fix attempt failed. Not for routine obvious failures; use for "ไล่บั๊ก".

ohm41321/luciazero · 57 tokens

tdd

Develop a feature or bug fix through a focused failing-test, minimal-implementation, and refactor loop. Use when the user requests TDD, asks for a regression test, or the bug has an obvious cheap local test target. Do not force TDD when the useful test path is unclear, expensive, or integration-heavy.

dayfinggg/openai-codex-agent-skills · 68 tokens

verification-loop

This skill should be used when the user asks to "verify code", "run verification", "check quality", "validate changes", or before creating a PR. Provides comprehensive verification including build, type check, lint, tests, security scan, and diff review.

Galaxy-Dawn/claude-scholar · 55 tokens

react-web

React web development with hooks, React Query, Zustand.

alinaqi/maggy · 13 tokens

iterative-development

TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.

alinaqi/maggy · 24 tokens

agent-session-format-check

Verify agent session format compatibility for Agent Sessions. Use when any agent CLI updates, when monitoring flags drift, or when bumping max verified versions (fixtures + docs + tests). Covers session schema, usage/limits tracking, storage backends, and discovery path contracts for all supported agents.

jazzyalex/agent-sessions · 62 tokens