round

An experiment-planning tool for machine-learning studies. It defines one question, separates settings being tested from incidental settings and fixed settings, and records the trial plan and budget.

In plain words
What is it for?
Use it to plan the next experiment, test whether a change helps, choose parameter ranges and a search method, and allocate trials.
Why use it?
It helps ensure that an experiment answers one clear question and that later results can be interpreted fairly.

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/emaballarin/ccplugins/round
Any agent
npx skills add emaballarin/ccplugins --skill round
Clone the repo
git clone --depth 1 https://github.com/emaballarin/ccplugins

Made for: Claude Code, Codex.

Per session 173 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,360 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 $0.00173 $0.01360
Opus 5 $0.00086 $0.00680
Sonnet 5 $0.00035 $0.00272
Haiku 4.5 $0.00017 $0.00136

Measured 2d ago against content hash 5c7a4f7c45f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

round 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.

plugins/tuneml/skills/round/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/tml:round — design the next experiment

Turn a question into a study whose answer will actually mean something. The whole value is in two things: one goal, and an honest scientific / nuisance / fixed split. Everything else is bookkeeping.

First action, always

ls -la ./.tml/rounds/ 2>/dev/null | tail -5; cat ./.tml/frontier.md 2>/dev/null | head -40

Number this round after the highest existing one. If earlier rounds exist, read the most recent spec and its verdict — a round that repeats a settled question is wasted budget, and a round that ignores the previous round's caveats inherits them silently.

Hard rules

  1. One goal per round. If the goal needs an "and", it is two rounds. Two simultaneous questions cannot be disentangled afterwards.
  2. Write the role assignment down. A round whose scientific / nuisance / fixed split was never recorded cannot be checked for fairness later — and it will be, by /tml:analyze, possibly in a different session.
  3. Every fixed hyperparameter is a caveat on the conclusion. Record it as one, in those words.
  4. Never put max_train_steps in the search space. Fixed per study.
  5. Read-first. Writes only under ./.tml/rounds/NNN/. Never runs training.

Procedure

1. Establish the regime — before designing anything

references/regime.md. Three questions: how many trials can run concurrently, where do they run, and does this plugin get to see the results directly. The answers change the design, not just its execution. Do not guess the trial capacity from device count.

2. Scope the goal

One sentence. references/study-design.md §1. Then state plainly whether this round is exploration (insight — the default and the majority) or exploitation (a best configuration). They use different samplers and have different success criteria.

3. Assign roles

references/hyperparameter-roles.md. In order:

  1. Name the scientific hyperparameters — usually one.
  2. Everything else starts nuisance.
  3. Demote nuisance → fixed deliberately, under budget pressure, preferring the ones that interact least with the scientific hyperparameters. Record each caveat.

Read the full file on GitHub · 118 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. 2d ago First seen · 118 lines · 173 tokens per session scan A 5c7a4f7c45f2

Subscribe to this mod's changes

round is a skill published in the GitHub repository emaballarin/ccplugins (3 stars, last pushed 26d ago), licensed MIT. It adds 173 tokens to every session and 1,360 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens