review

A read-only reviewer for changes to machine-learning training or evaluation pipelines. It checks whether the claimed mechanism ran, whether the measurement remains valid, and what the change may have broken.

In plain words
What is it for?
Use it to review a training or evaluation diff, investigate unexpected performance changes, or challenge claims such as improved throughput.
Why use it?
A faster pipeline is not necessarily a better one: the speedup may be inactive, measured incorrectly, or harmful to results. This review looks for evidence behind the claim before a change is merged.

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

Made for: Claude Code, Codex.

Per session 204 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,325 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 $0.00204 $0.01325
Opus 5 $0.00102 $0.00662
Sonnet 5 $0.00041 $0.00265
Haiku 4.5 $0.00020 $0.00133

Measured 2d ago against content hash 668b668ec2d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review 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/review/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/tml:review — did it work, and what did it cost

Adversarial by construction. The default posture is that the change did not do what it claims, and the review's job is to find out whether that default survives contact with the diff.

Hard rules

  1. Read-only. No edits, no writes, not even to ./.tml/. Verdicts only.
  2. Three questions, always, in order: did the mechanism engage, is the measurement still valid, what did it silently break.
  3. "Improved throughput" is not an answer to any of them.
  4. A verdict without a check behind it is an opinion. Name the file, the line, the trace, or the number.

Procedure

1. What is claimed, and what would falsify it

State the claim in one sentence, then its radius (references/evidence-grades.md §3.1) read mechanically off the diff, then what observation would show it false. If nothing would, say so — an unfalsifiable claim is the finding.

2. Did the mechanism engage

The most common failure is a change that is present in the source and inert at runtime:

  • A flag set after the object it configures was constructed.
  • A fast path guarded by a condition that never holds — dtype, shape, contiguity, device, or a version check.
  • A compiled path recompiling every step (count the recompilations; a recompilation per step is worse than no compilation).
  • A kernel that silently fell back because its workspace did not fit — which is also why an interior batch-size optimum can appear (tier-b-systems.md B14).
  • An optimiser change where the beta convention differs between algorithms: Adan's β₂ is not Adam's β₂, Adan's β₃ is, RMSProp's alpha is, and PyTorch's SGD momentum decays a sum rather than an average (references/optimisers.md §1). A ported beta value is a silent learning-rate change. Check this whenever an optimiser was swapped or its hyperparameters were copied from elsewhere.
  • Weight decay carried across an Adam → AdamW boundary unchanged — different hyperparameter, different scale (optimisers.md §2).

Read the full file on GitHub · 106 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 · 106 lines · 204 tokens per session scan A 668b668ec2d5

Subscribe to this mod's changes

review is a skill published in the GitHub repository emaballarin/ccplugins (3 stars, last pushed 26d ago), licensed MIT. It adds 204 tokens to every session and 1,325 once invoked, about $0.0010 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

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

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens