lemma-evals

lemma-evals is a skill for Codex from lemma-work/lemma-platform. It costs 102 tokens per session (3,138 once invoked), scanned A, original, AGPL-3.0.

A skill for designing, running, and reviewing repeatable evaluations of Lemma agents, functions, and workflows. An evaluation is a set of tests used to check whether a system behaves as intended.

In plain words
What is it for?
Use it to define evaluation criteria and test datasets, compare revisions or runtimes, measure repeated-run variation, and review deterministic or rubric-based results.
Why use it?
It makes changes easier to compare by testing a baseline and a candidate version against the same cases and examining correctness and consistency.

Skill for Codex

Written for Codex: agents/openai.yaml present.

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/lemma-work/lemma-platform/lemma-evals
Any agent
npx skills add lemma-work/lemma-platform --skill lemma-evals
Clone the repo
git clone --depth 1 https://github.com/lemma-work/lemma-platform

Made for: 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 lemma-evals

README.md
[![agentmods](https://agentmods.dev/badge/skills/lemma-work/lemma-platform/lemma-evals.svg)](https://agentmods.dev/skills/lemma-work/lemma-platform/lemma-evals)
Your own site
<a href="https://agentmods.dev/skills/lemma-work/lemma-platform/lemma-evals"><img src="https://agentmods.dev/badge/skills/lemma-work/lemma-platform/lemma-evals.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 3,138 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.03138
Opus 5 $0.00051 $0.01569
Sonnet 5 $0.00020 $0.00628
Haiku 4.5 $0.00010 $0.00314

Measured 2d ago against content hash f877e5643957, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

lemma-evals 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.

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.

lemma-skills/lemma-evals/SKILL.md · 280 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

Files

What ships with it

2 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. 2d ago Changed · +27 lines f877e5643957
  2. 6d ago First seen · 253 lines · 102 tokens per session scan A 6ac67c175752

Subscribe to this mod's changes

lemma-evals is a skill published in the GitHub repository lemma-work/lemma-platform (387 stars, last pushed today), licensed AGPL-3.0. It adds 102 tokens to every session and 3,138 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 2026-08-30.

Related

Other skills, from other repositories

verify-before-done

Proving a change works before reporting it done, and what to do when the check fails. Use after editing code, before writing the final answer, and whenever deciding which check proves which claim.

Zfinix/aster · 44 tokens

write-tests

Writing tests that catch regressions instead of restating the code. Use when adding tests, when a fix needs a regression test, or when the user asks for coverage.

Zfinix/aster · 37 tokens

create-aoh-pack

Use when creating or revising reusable Agentic Ops Harness packs, ops skills, workflows, agent roles, model profiles, runtime requirements, evals, or runtime adapter mappings.

agenticdevops/aoh · 40 tokens

aster-ui-demo

How to demo UI work the way Claude does it, never with throwaway HTML mockups. Build the change in the real webview, verify it in the browser harness, open the live dev server for the user to click through, and run the real test suites. Use when the user asks for a demo, a preview, or "let me see" any UI change in the…

Zfinix/aster · 87 tokens

building-pydantic-ai-agents

Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydanticai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents…

pydantic/pydantic-ai · 85 tokens

benchmark-design

Design and calibrate a multi-Case capability Benchmark and establish a traceable Formal Baseline.

Prism-Shadow/penguin-harness · 22 tokens