eval

A command for eval-driven development, where a feature is checked against written capability and regression criteria. An eval is a repeatable check of whether the expected behavior works.

In plain words
What is it for?
Use it to define, run, list, and report checks for a feature, including capability tests and regression tests.
Why use it?
It records what success means and tracks failed or passing checks instead of relying only on informal testing. This helps catch both missing features and broken existing behavior.

Command

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 commands/rohitbind123/claude-setup/eval
Clone the repo
git clone --depth 1 https://github.com/RohitBind123/claude-setup
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 609 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 89% 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 $0.00000 $0.00609
Opus 5 $0.00000 $0.00304
Sonnet 5 $0.00000 $0.00122
Haiku 4.5 $0.00000 $0.00061

Measured yesterday against content hash 7c8e20c65995, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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

89% identical to eval — 4 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.

commands/eval.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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:
## 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
  1. 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)

Read the full file on GitHub · 121 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. yesterday First seen · 121 lines · 0 tokens per session scan A 7c8e20c65995

Subscribe to this mod's changes

eval is a command published in the GitHub repository RohitBind123/claude-setup (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 609 tokens. A static security scan graded it A with 0 findings. It is 89% identical to eval, differing in 4 lines, and is treated as a copy.