lastlight-evals

lastlight-evals is a skill for Claude Code from nearform/lastlight. It costs 185 tokens per session (4,965 once invoked), scanned A, original, MIT.

An evaluation workspace for running Last Light's coding-agent workflows against a simulated GitHub and scoring the results with fixed rules. It can also compare models by success rate, cost, and response time.

In plain words
What is it for?
Use it to create an evaluation workspace, run tests, compare models, review past runs, or build test cases from GitHub issues and pull requests.
Why use it?
It lets you test agent workflows in repeatable conditions without changing a real GitHub repository.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is lastlight-evals add-case --pr <github-pr-url> --review # write into ./datasets/pr-review (or --overlay).

Part of the lastlight plugin — 7 skills shipped together

Good fit Use it to create an evaluation workspace, run tests, compare models, review past runs, or build test cases from GitHub issues and pull requests.

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/nearform/lastlight
agentmods
npx agentmods add skills/nearform/lastlight/lastlight-evals

Made for: Claude Code.

Or install lastlight, the plugin that ships this one along with the rest of its 7 skills.

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 lastlight-evals

README.md
[![agentmods](https://agentmods.dev/badge/skills/nearform/lastlight/lastlight-evals.svg)](https://agentmods.dev/skills/nearform/lastlight/lastlight-evals)
Your own site
<a href="https://agentmods.dev/skills/nearform/lastlight/lastlight-evals"><img src="https://agentmods.dev/badge/skills/nearform/lastlight/lastlight-evals.svg" alt="Measured on agentmods" height="20"></a>
Per session 185 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,965 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 165
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 166
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 214
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
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 $0.00185 $0.04965
Opus 5 $0.00093 $0.02482
Sonnet 5 $0.00037 $0.00993
Haiku 4.5 $0.00018 $0.00496

Measured 8d ago against content hash a50e228035a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

lastlight-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 8d 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.

plugins/lastlight/skills/lastlight-evals/SKILL.md · 309 lines

How it starts

The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Set up & run Last Light Evals

lastlight-evals runs Last Light's real production workflows (issue-triage, build, …) end-to-end against a mocked GitHub, grades the results deterministically (no LLM-as-judge), and compares models on pass rate, cost, and latency. It's a thin CLI on top of the lastlight core package (via the lastlight/evals barrel), so it exercises the same workflows/skills production does. SWE-bench compatible. Node 24+.

Start here — what do you want to do?

If the user's evals goal is clear, jump to the section. If it's vague ("help me with the evals", "what can this do?"), ask (AskUserQuestion) which of these they want, then go:

Goal Section
Set up an evals workspace (first time) §2 Scaffold (+ §1 prereqs, §3 providers)
Run evals / compare models §4 Run
Look at past runs (no models run) §4lastlight-evals serve
Author one case from a GitHub PR or issue §6
Build a PR-review dataset from my own gold PRs §6 → "Build a PR-review dataset"
Add cases by hand / understand the schema §5 + references/instance-schema.md
Iteratively improve the score toward a target the lastlight-evals-loop skill

New to the whole plugin (server / overlay / client, not just evals)? That's the lastlight-guide skill — this one is evals-only.

1. Check prerequisites

node --version    # need >= 24
command -v lastlight-evals >/dev/null && echo "installed" || npm i -g lastlight-evals
lastlight-evals --version   # prints the evals version + the bundled lastlight core version
# Optional: for `--sandbox gondolin` (isolate the agent in a QEMU micro-VM so it
# can't read host gold data) you also need QEMU natively: `brew install qemu`
# (macOS) or your distro's `qemu-system` package. The default `--sandbox none`
# needs nothing extra.

2. Scaffold a workspace

init is non-interactive when there's no TTY (piped/agent/CI) — it never blocks on a prompt. Two layouts:

Read the full file on GitHub · 309 lines

Files

What ships with it

4 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. 8d ago First seen · 309 lines · 185 tokens per session scan A a50e228035a7

Subscribe to this mod's changes

lastlight-evals is a skill published in the GitHub repository nearform/lastlight (22 stars, last pushed 4d ago), licensed MIT. It adds 185 tokens to every session and 4,965 once invoked, about $0.0009 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.