loopx-benchmark

A workflow for running and evaluating LoopX benchmark experiments, which compare how different automated approaches perform on the same tasks.

In plain words
What is it for?
Use it to inspect benchmark capabilities, manage experiment-board entries, qualify results, classify output files, and analyze matched comparisons.
Why use it?
It keeps experiment records, source versions, result integrity, and comparisons consistent instead of relying on informal notes.

Skill for Claude CodeCodex

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/huangruiteng/loopx/loopx-benchmark
Any agent
npx skills add huangruiteng/loopx --skill loopx-benchmark
Clone the repo
git clone --depth 1 https://github.com/huangruiteng/loopx

Made for: Claude Code, Codex.

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,724 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 $0.00069 $0.01724
Opus 5 $0.00034 $0.00862
Sonnet 5 $0.00014 $0.00345
Haiku 4.5 $0.00007 $0.00172

Measured yesterday against content hash a158afdbad3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

loopx-benchmark 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 yesterday.

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/loopx-benchmark/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LoopX Benchmark Workflow

Use this skill for a LoopX-managed benchmark experiment. The builtin benchmark-toolkit capability owns provider-neutral experiment state and integrity boundaries. This packaged skill is its task-triggered Agent playbook.

The capability is catalog-ready without a per-Goal enable switch. Installing this skill does not grant runner, shell, network, credential, private-evidence, or Goal mutation authority. Respect the selected todo's required capabilities, any external provider binding, host permissions, and user gates.

Capability surface

  • loopx capability show benchmark-toolkit --format json — catalog entry with usage hints, role boundaries, and the post-run case-insight template.
  • loopx benchmark --help — subcommands (experiment-board-show, experiment-board-upsert, source-revision-fence, integrity-qualification, classify-artifacts).

Select the operating lane

  • Inspect or explain: use capability show and benchmark --help; remain read-only. Do not create an experiment-board row merely because the user asks what the toolkit does.
  • Plan, select, or launch a run: follow the experiment sequence below. The first action is to read the board; a launch still requires an authorized runner and admitted source.
  • Monitor an active campaign: read the board and runtime-owned projections; update only on material run transitions. Do not manufacture progress from a timer tick.
  • Analyze a terminal run: wait until solving is terminal and scoring is complete before reading hidden evaluator evidence or writing a case insight.

For a generic library microbenchmark or an eval with no LoopX Goal/board, use the task's normal tools instead of imposing this workflow.

Experiment sequence

  1. Read the experiment board before launching or selecting a case.
    loopx benchmark experiment-board-show --goal-id <GOAL_ID> --format json
    
    Inspect baseline, treatment, explore, countability, effort, and insight rows before choosing the next arm.

Read the full file on GitHub · 149 lines

Files

What ships with it

1 file 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. yesterday First seen · 149 lines · 69 tokens per session scan A a158afdbad3f

Subscribe to this mod's changes

loopx-benchmark is a skill published in the GitHub repository huangruiteng/loopx (5,313 stars, last pushed yesterday), licensed Apache-2.0. It adds 69 tokens to every session and 1,724 once invoked, about $0.0003 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.