nasde-benchmark-runner

nasde-benchmark-runner is a skill for Claude Code, Codex from NoesisVision/nasde-toolkit. It costs 139 tokens per session (7,789 once invoked), scanned A, original, MIT.

A benchmark runner for testing coding agents on programming tasks. It uses Docker containers to check whether tasks work, then uses an AI judge to assess code structure and quality.

In plain words
What is it for?
Running all, selected, or variant-specific coding-agent benchmarks; re-running evaluations on existing results; and checking traces, feedback scores, and experiments in Opik.
Why use it?
It removes the manual work of running the same tests, reviewing results, and comparing agent performance. It also helps investigate failed runs and inspect recorded evaluation data.

Skill for Claude CodeCodex

Written for Claude Code and Codex: installed under .claude/, but also reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions CLAUDE.md; 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/noesisvision/nasde-toolkit/nasde-benchmark-runner
Any agent
npx skills add NoesisVision/nasde-toolkit --skill nasde-benchmark-runner
Clone the repo
git clone --depth 1 https://github.com/NoesisVision/nasde-toolkit

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 nasde-benchmark-runner

README.md
[![agentmods](https://agentmods.dev/badge/skills/noesisvision/nasde-toolkit/nasde-benchmark-runner.svg)](https://agentmods.dev/skills/noesisvision/nasde-toolkit/nasde-benchmark-runner)
Your own site
<a href="https://agentmods.dev/skills/noesisvision/nasde-toolkit/nasde-benchmark-runner"><img src="https://agentmods.dev/badge/skills/noesisvision/nasde-toolkit/nasde-benchmark-runner.svg" alt="Measured on agentmods" height="20"></a>
Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,789 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00139 $0.07789
Opus 5 $0.00069 $0.03895
Sonnet 5 $0.00028 $0.01558
Haiku 4.5 $0.00014 $0.00779

Measured 6d ago against content hash d104b674e93f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

nasde-benchmark-runner scanned grade A with 1 finding 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 6d ago.

The scan reads SKILL.md. This mod also ships 7 executable files (scripts/export_codex_oauth_token.ps1, scripts/export_codex_oauth_token.sh, scripts/export_gemini_oauth_token.ps1, …), 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Use Python `urllib.request` (never curl — it drops the `Comet-Workspace` header):
.claude/skills/nasde-benchmark-runner/SKILL.md · 521 lines

How it starts

The opening of the file, as written. The whole thing — 521 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NASDE Benchmark Runner

Run coding agent benchmarks with nasde and verify results. The two-stage pipeline: Harbor runs agents in Docker containers (functional test → reward 0/1), then an LLM-as-a-Judge scores architecture quality across multiple dimensions.

Authentication setup

Before running any benchmark, set up authentication tokens for the agents you plan to run. Both OS and auth method matter — pick the right command per row.

Step 1 — Ask the user which auth they prefer

Always ask the user before running, never assume. Two questions:

  1. Which agents will you run? (Claude / Codex / Gemini, any combination)
  2. For each agent, OAuth (subscription) or API key (per-token billing)? Default recommendation: OAuth where available — no per-token cost, no env vars to manage.

Then detect their OS and pick the matching script row from the table below. On Windows, also ask whether they're in PowerShell or WSL (cmd.exe is not directly supported — see "Windows: cmd.exe" below).

Where the auth scripts live

The OAuth scripts ship inside this skill. After nasde install-skills they are at:

  • User scope (default): ~/.claude/skills/nasde-benchmark-runner/scripts/ (macOS/Linux/WSL) or %USERPROFILE%\.claude\skills\nasde-benchmark-runner\scripts\ (Windows PowerShell)
  • Project scope: <project>/.claude/skills/nasde-benchmark-runner/scripts/ (if installed with nasde install-skills --scope project)
  • Editable nasde checkout (devs only): <repo>/scripts/ — same files, mirrored from the skill bundle

Below, <SKILL_SCRIPTS> is shorthand for whichever absolute path applies. Resolve it once, then substitute it in every command. Verify the path with ls <SKILL_SCRIPTS> before telling the user to source anything — if the directory is missing, they need to run nasde install-skills first.

Step 2 — Run the right script per agent × OS

Priority order: Claude → Codex → Gemini. Claude is required even for non-Claude variants when [evaluation] backend = "claude" (default), because the assessment evaluator spawns claude CLI as a subprocess.

Read the full file on GitHub · 521 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. 6d ago First seen · 521 lines · 139 tokens per session scan A d104b674e93f

Subscribe to this mod's changes

nasde-benchmark-runner is a skill published in the GitHub repository NoesisVision/nasde-toolkit (12 stars, last pushed today), licensed MIT. It adds 139 tokens to every session and 7,789 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.