eval-loop

eval-loop is a skill for Claude Code, Codex from malloydata/publisher. It costs 102 tokens per session (4,315 once invoked), scanned A, original, MIT.

A local evaluation workflow for testing an AI model or agent across a set of cases. It runs answers, scores them, investigates failures, applies carefully limited improvements, and records checkpoints.

In plain words
What is it for?
Use it to run evaluation datasets, identify shared failure causes, update model guidance, and verify whether each change helps.
Why use it?
It provides a repeatable way to improve answer quality without mixing scoring, diagnosis, and editing into one step. Checkpoints make accepted changes easier to track and undo.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

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 skills/malloydata/publisher/eval-loop
Any agent
npx skills add malloydata/publisher --skill eval-loop
Clone the repo
git clone --depth 1 https://github.com/malloydata/publisher

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 eval-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/malloydata/publisher/eval-loop.svg)](https://agentmods.dev/skills/malloydata/publisher/eval-loop)
Your own site
<a href="https://agentmods.dev/skills/malloydata/publisher/eval-loop"><img src="https://agentmods.dev/badge/skills/malloydata/publisher/eval-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,315 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00102 $0.04315
Opus 5 $0.00051 $0.02158
Sonnet 5 $0.00020 $0.00863
Haiku 4.5 $0.00010 $0.00432

Measured 2d ago against content hash 0c9faa416e55, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

eval-loop 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 2d ago.

The scan reads SKILL.md. This mod also ships 8 executable files (scripts/agent_harness.py, scripts/build_run_package.py, scripts/check_judge.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/eval-loop/SKILL.md · 350 lines

How it starts

The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The Evaluation Loop

You conduct this loop. There is no batch orchestrator to start, no eval API, and no eval MCP tools. The ledger is plain files in the model package's git repository (reference/ledger-schema.md in skill:eval-answer defines every file and event). Scoring is an LLM judge you spawn per case. There is no scripted scorer, and there will not be one: a script that can pass a wrong answer is worse than none. The scripts under scripts/ run the loop -- they answer, re-execute, spawn the judge, compare runs, and write the ledger -- but none of them decides whether an answer was right.

scrape/run  ->  eval  ->  diagnose  ->  improve  ->  checkpoint

This skill conducts; it does not restate. Scoring lives in skill:eval-answer. Components and owners live in skill:eval-diagnose. Edit rules live in skill:eval-improve.

Do not merge eval into diagnose. A conductor who scores while explaining writes the explanation into the score. Do not skip the acceptance check inside improve. The acceptance check decides whether this edit stays. Checkpoint decides whether a sequence of accepted edits can be undone.

Where the rest of this lives

This file is the procedure. Five things it used to carry inline are files beside it now, because each is needed at one moment rather than every run, and loading all of them for every run is how a skill stops being read.

When Read
about to run one reference/running-a-run.md
a golden is wrong, doubted, or out of step with the model reference/golden-side-door.md
deciding whether an edit stays reference/acceptance-check.md
about to quote a number, or set the noise band reference/measurement.md
you changed judge doctrine or its inputs reference/checking-the-judge.md

Read the file, do not work from the summary here. The acceptance-check rules and the golden side door are both places where acting on a half-memory of the rule produces a confident wrong answer rather than an error.

Read the full file on GitHub · 350 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. 2d ago First seen · 350 lines · 102 tokens per session scan A 0c9faa416e55

Subscribe to this mod's changes

eval-loop is a skill published in the GitHub repository malloydata/publisher (100 stars, last pushed today), licensed MIT. It adds 102 tokens to every session and 4,315 once invoked, about $0.0005 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

dbt-expert

Expert-level dbt (data build tool), models, tests, documentation, incremental models, macros, and Jinja templating. Use when the user mentions analytics engineering, SQL, data transformation, Jinja, or testing, or when the task involves Project Structure and Configuration, Sources and Staging Models, Intermediate and…

personamanagmentlayer/pcl · 76 tokens

reusable-visualization

Build ONE reusable chart visualization component that receives its data and its settings from the host application instead of fetching them, and declares the fields and config options the host exposes to viewers. Use this whenever a single chart component is reused across many different queries rather than built for…

lightdash/lightdash · 102 tokens

lightdash-agent-slack-messaging

Use this skill when writing, designing, or generating Slack messages for Lightdash's in-app analytics agent. Triggers when someone asks to create agent update messages, Slack digests, agent notifications, weekly summaries, daily summaries, or any Slack copy for the Lightdash project agent. Also use when asked to vary…

lightdash/lightdash · 114 tokens

upgrade-preflight

Checks whether a self-hosted Lightdash upgrade is safe to run, and reads the tooling's answer without over-reading it. Use when upgrading a self-hosted instance, planning a maintenance window, answering "is this upgrade safe", or recovering a failed, hung, parked or lock-stuck migration — covers lightdash…

lightdash/lightdash · 101 tokens

developing-in-lightdash

Use when reading, creating, and editing Lightdash dashboards and charts as JSON, including dashboard layout and chart-type-specific configuration.

lightdash/lightdash · 31 tokens

developing-data-apps-locally

Use when editing a locally created or downloaded Lightdash data app — how local editing, building, and uploading work, and what is read-only.

lightdash/lightdash · 38 tokens