eval-iterate

eval-iterate is a skill for Claude Code from mthines/agent-skills. It costs 252 tokens per session (4,409 once invoked), scanned A, original, MIT.

A workflow for fixing failing evaluations of AI systems, including test suites, expected-answer sets, and grader-based checks.

In plain words
What is it for?
It supports diagnosing failures, applying minimal fixes, rerunning evaluations, and confirming that they pass consistently.
Why use it?
It helps distinguish faulty code from outdated tests, changing grading rules, or unreliable results without weakening the evaluation.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/eval/l1.mjs # deterministic contract checks.

Part of the mthines-agent-skills plugin — 55 skills, 4 agents shipped together

Good fit It supports diagnosing failures, applying minimal fixes, rerunning evaluations, and confirming that…

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/mthines/agent-skills
agentmods
npx agentmods add skills/mthines/agent-skills/eval-iterate

Made for: Claude Code.

Or install mthines-agent-skills, the plugin that ships this one along with the rest of its 55 skills, 4 agents.

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-iterate

README.md
[![agentmods](https://agentmods.dev/badge/skills/mthines/agent-skills/eval-iterate.svg)](https://agentmods.dev/skills/mthines/agent-skills/eval-iterate)
Your own site
<a href="https://agentmods.dev/skills/mthines/agent-skills/eval-iterate"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/eval-iterate.svg" alt="Measured on agentmods" height="20"></a>
Per session 252 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,409 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 $0.00252 $0.04409
Opus 5 $0.00126 $0.02204
Sonnet 5 $0.00050 $0.00882
Haiku 4.5 $0.00025 $0.00441

Measured 3d ago against content hash 5d2632e91d32, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

eval-iterate 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 3d 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.

skills/quality/eval-iterate/SKILL.md · 357 lines

How it starts

The opening of the file, as written. The whole thing — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eval Iterate

Drive a failing AI/LLM eval to a real green: diagnose, fix, re-run, confirm — capped at 5 iterations, never by weakening the eval.

This SKILL.md is the orchestration index. Load the matching rule file when you need detail — do not preload them.

Phase Goal Required rule
0 Resolve the target eval + capture the baseline failure this file
1 Resolve how to run it this file
2 Classify the failure (verdict required) rules/eval-bug-classification.md
3 Apply the minimal fix — gated if it touches the eval itself rules/anti-gaming-guard.md
4 Re-run, then confirm with a second run rules/convergence-confirmation.md
5 Iterate or stop at the cap this file
6 Report (structured exit summary) this file

Always read rules/anti-gaming-guard.md before touching any eval definition (assertion, threshold, golden-set item, judge prompt). The refusals in it apply on every iteration.

Input

The user provides one of:

  • An eval identifier — an L2 suite name (e.g. tier-routing), a golden-set file path, or a test/eval file path.
  • A PR URL with a failing eval check.
  • Nothing — if $ARGUMENTS is empty, auto-detect the failing eval check on the current branch's open PR (see Phase 0).
  • --max-iterations <n> — lowers the cap below 5. Never raises it. A value above 5 is clamped to 5, not honored.

The argument is: $ARGUMENTS.

Phase 0 — Resolve the target + capture the baseline

If $ARGUMENTS is empty, do not ask the user — resolve automatically:

  1. Get the current branch and its open PR:
    git rev-parse --abbrev-ref HEAD
    gh pr list --head "<branch>" --state open --json number,url --limit 1
    
  2. List failing checks and find the one that is an eval (name contains eval, l2, or matches a known suite):
    gh pr checks <pr-number> --repo <owner/repo>
    
  3. If exactly one failing eval check is found, use it as the target. If more than one, list them and ask the user which to iterate on first — this skill iterates on one target at a time. If none is found, report that and stop; there is nothing to iterate on.

Read the full file on GitHub · 357 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 357 lines · 252 tokens per session scan A 5d2632e91d32

Subscribe to this mod's changes

eval-iterate is a skill published in the GitHub repository mthines/agent-skills (12 stars, last pushed yesterday), licensed MIT. It adds 252 tokens to every session and 4,409 once invoked, about $0.0013 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

coverage-tracker

Run a Google Alerts-style keyword coverage tracker. Uses news-search for recent keyword queries, lets the LLM dedupe and classify real features versus junk, stores decisions in SQLite, and alerts only on new real coverage.

elvisun/newsjack · 47 tokens

prompt-set-qa

Gate a prompt universe for schema and provenance completeness, target or campaign contamination, evidence entailment, naturalness, one-concept clarity, architecture consistency, aided status, answer leakage, and semantic duplicates. Use after realistic prompt generation and before human panel selection.

elvisun/newsjack · 56 tokens

realistic-prompt-generation

Generate natural, controlled prompt variants from a target-blind design brief and prompt architecture while preserving approved jobs, acts, journeys, constraints, roles, locales, proximity bands, and evidence language. Use after architecture design and before contamination or semantic QA.

elvisun/newsjack · 55 tokens

ai-visibility-panel-design

Select QA-approved canonical intent cells into a versioned AI-visibility tracking panel with partitions, variants, lanes, surfaces, locales, repetitions, separate exposure and priority weights, randomization, uncertainty, refresh rules, and campaign controls. Use after prompt QA or when revising an existing panel.

elvisun/newsjack · 64 tokens

smoke-test-ml-pipeline

Owns the smoke test contract for an ML experiment: a small, diagnostic-by-construction pytest that fits the experiment's learner on a portion of the real data/ source and predicts on a disjoint portion that deliberately carries no pre-history buffer. The assertion is structural — the number of predictions must equal…

probabl-ai/skills · 486 tokens

write-kaggle-benchmarks

Write, push, run, publish, and manage Kaggle Benchmark tasks using the kaggle CLI and the kaggle-benchmarks Python SDK. Use when the user wants to create or push a benchmark task (optionally with attached Kaggle datasets), run benchmarks against LLM models, check task/run status, stream or fetch execution logs…

Kaggle/kaggle-skills · 95 tokens