Skip to main content
command CX Codex

eval · sangrokjung — Claude Code command: what it does, how to install

This command defines eval criteria, runs checks, and builds reports. Use it to track a feature’s capabilities and catch regressions against a baseline.

MIT ★ 880 updated 2026-09-03

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/commands/eval.md
Open on GitHub

What eval does

/eval define <name> creates a criteria file under .claude/evals/ and asks the user to fill in feature-specific checks. The template separates capability and regression evals. Its success criteria set pass@3 > 90% for capability evals and pass^3 = 100% for regression evals.

/eval check <name> attempts each capability check, runs relevant regression tests, compares them with a baseline, and logs attempts. That baseline comparison matters: it is how the command checks for regressions. /eval report <name> produces results, metrics, notes, and a recommendation; /eval list shows definitions and their status. The clean argument removes old eval logs while keeping the last 10 runs.

What it helps with

  • define checks for a new feature
  • record capability-check attempts in a log
  • compare regression tests with a baseline
  • generate a report with metrics and a recommendation
  • list eval definitions and their status

Example prompts for the agent

  • Define eval criteria for the search feature.
  • Check evals for feature-auth and compare regression tests with the baseline.
  • Generate a report for feature-export, then list the eval definitions.

How to install eval

Manually: put the files in place

.claude/commands/eval.md

Call it with /eval. For all projects use ~/.claude/commands/

Questions about eval

How do I install eval in Claude Code?

Create .claude/commands/eval.md and place the command contents in that file. Then invoke it with /eval.

What does the eval command do?

It creates eval definitions, runs checks, generates reports, and lists features with their current status.

How does eval check regressions?

It runs relevant tests, compares their results against a baseline, and records each result as PASS or FAIL.

Source text

eval.md · MIT
---
description: Manage eval-driven development workflow (define, check, report, list)
---

# Eval Command

Manage eval-driven development workflow.

## Usage

`/eval [define|check|report|list] [feature-name]`

## Define Evals

`/eval define feature-name`

Create a new eval definition:

1. Create `.claude/evals/feature-name.md` with template:

```markdown
## EVAL: feature-name
Created: $(date)

### Capability Evals
- [ ] [Description of capability 1]
- [ ] [Description of capability 2]

### Regression Evals
- [ ] [Existing behavior 1 still works]
- [ ] [Existing behavior 2 still works]

### Success Criteria
- pass@3 > 90% for capability evals
- pass^3 = 100% for regression evals
```

2. Prompt user to fill in specific criteria

## Check Evals

`/eval check feature-name`

Run evals for a feature:

1. Read eval definition from `.claude/evals/feature-name.md`
2. For each capability eval:
   - Attempt to verify criterion
   - Record PASS/FAIL
   - Log attempt in `.claude/evals/feature-name.log`
3. For each regression eval:
   - Run relevant tests
   - Compare against baseline
   - Record PASS/FAIL
4. Report current status:

```
EVAL CHECK: feature-name
========================
Capability: X/Y passing
Regression: X/Y passing
Status: IN PROGRESS / READY
```

## Report Evals

`/eval report feature-name`

Generate comprehensive eval report:

```
EVAL REPORT: feature-name
=========================
Generated: $(date)

CAPABILITY EVALS
----------------
[eval-1]: PASS (pass@1)
[eval-2]: PASS (pass@2) - required retry
[eval-3]: FAIL - see notes

REGRESSION EVALS
----------------
[test-1]: PASS
[test-2]: PASS
[test-3]: PASS

METRICS
-------
Capability pass@1: 67%
Capability pass@3: 100%
Regression pass^3: 100%

NOTES
-----
[Any issues, edge cases, or observations]

RECOMMENDATION
--------------
[SHIP / NEEDS WORK / BLOCKED]
```

## List Evals

`/eval list`

Show all eval definitions:

```
EVAL DEFINITIONS
================
feature-auth      [3/5 passing] IN PROGRESS
feature-search    [5/5 passing] READY
feature-export    [0/4 passing] NOT STARTED
```

## Arguments

$ARGUMENTS:
- `define <name>` - Create new eval definition
- `check <name>` - Run and check evals
- `report <name>` - Generate full report
- `list` - Show all evals
- `clean` - Remove old eval logs (keeps last 10 runs)

© sangrokjung · MIT · sangrokjung/claude-forge

Similar slash commands

All slash commands for Testing and QA →

eval by other authors comes first.

eval Seth Hobson Evaluates a plugin or skill directory using static checks and an LLM judge. Spots anti-patterns and scores quality up to 100 points. CX Codex +1 ★ 42,780repo stars eval-harness affaan-m eval-harness — a skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode that brings eval-driven development into every agent session: success criteria go in before any code, results are scored with pass@k and pass^k. CX Codex +1 6,500installs google-agents-cli-eval official Google google-agents-cli-eval runs agent evaluation pipelines, grades responses with LLM judges, and tracks metric failures. Activates during dataset authoring and benchmark runs in agents-cli. CX Codex +1 586,000installs bmad-eval bmad-code-org bmad-eval — a skill for Claude Code, Codex, Cursor and Copilot that runs another skill's test suite and reports findings. Triggers when you need to check description accuracy, compare versions or grade output against a rubric. CX Codex +1 9,100installs eval-runner haabe eval-runner — a skill for Claude Code, Codex, Cursor and other agents that runs YAML eval scenarios through a reflexion loop and writes results to JSON. CX Codex +1 ★ 54repo stars llm-eval-harness daymade llm-eval-harness — a skill for Claude Code, Codex, Cursor, and other platforms that probes a third-party LLM endpoint for availability, speed, system-prompt fidelity, and protocol correctness. CX Codex +1 438installs eval-grader serpro69 eval-grader — a grader for skill-eval assertions that returns PASS, FAIL or PARTIAL on each, with one line of evidence. Handy when a reviewer's write-up needs a verdict from something that did not produce it. CX Codex ★ 155repo stars

From the same set44

The whole set →
korean-spell-check korean-spell-check — a Claude Code skill that checks Korean spelling and returns edits instead of a rewritten draft. Long input gets split into chunks before it goes out. CX Codex +1 ★ 880repo stars instinct-status Review learned instincts with their confidence levels, domains, and sources. Use the command to inspect what the agent has picked up from its observations. CX Codex +1 ★ 880repo stars doc-updater doc-updater rebuilds README, guides and codemaps from the actual source after code changes. Useful once the docs have drifted away from the code. CX Codex ★ 880repo stars instinct-export instinct-export exports continuous-learning instincts into a shareable file for team members or migration across machines. CX Codex +1 ★ 880repo stars refactor-cleaner refactor-cleaner — a subagent that hunts down code nobody calls: unused files, exports and npm packages. Each hit gets a reference search before anything is deleted. CX Codex ★ 880repo stars task-grade-routing task-grade-routing sets documentation and review lane obligations for task sizes S, M, L, and XL based on workflow classification. CX Codex +1 ★ 880repo stars frontend-code-review The frontend-code-review skill checks frontend files against a checklist and formats findings in a fixed review structure. Use it for pending changes or specific files you name. CX Codex +1 ★ 880repo stars instinct-import instinct-import pulls instincts from a file or URL, checks them against the ones you already have, and files the keepers with a note of where they came from. CX Codex +1 ★ 880repo stars

Project sponsors

Companies that keep this analytics open