agentmods.dev

review-test

review-test is a command for Claude Code from OleksiiDotsenko/english-exam-coach. It costs 21 tokens per session (376 once invoked), scanned A, original, MIT.

A command for recording and reviewing a complete English test taken elsewhere. It stores the test scores and mistakes, then compares the results with earlier tests.

In plain words
What is it for?
Use it to log scores, import tagged mistakes, review a selected test, and maintain records for yourself or for another learner.
Why use it?
It keeps evidence from an external test in one review record without guessing about missing information. This makes changes in scores and repeated error patterns easier to inspect.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the english-exam-coach plugin — 1 skill, 9 commands shipped together

not rated 10repo changed 28d ago A scan 21 tokens original MIT

Good fit Use it to log scores, import tagged mistakes, review a selected test, and maintain records for yourself or for another learner.

Compare 6 commands from other repositories ↓
View source ↗ OleksiiDotsenko/english-exam-coach
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add OleksiiDotsenko/english-exam-coach
Claude Code
/plugin install english-exam-coach

Made for: Claude Code.

Or install english-exam-coach, the plugin that ships this one along with the rest of its 1 skill, 9 commands.

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 review-test

README.md
[![agentmods](https://agentmods.dev/badge/commands/oleksiidotsenko/english-exam-coach/review-test/github.svg)](https://agentmods.dev/commands/oleksiidotsenko/english-exam-coach/review-test)
Your own site
<a href="https://agentmods.dev/commands/oleksiidotsenko/english-exam-coach/review-test"><img src="https://agentmods.dev/badge/commands/oleksiidotsenko/english-exam-coach/review-test/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for review-test

Your own site · 80×15
<a href="https://agentmods.dev/commands/oleksiidotsenko/english-exam-coach/review-test"><img src="https://agentmods.dev/badge/commands/oleksiidotsenko/english-exam-coach/review-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 376 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.
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 $0.00021 $0.00376
Opus 5.5 $0.00008 $0.00150
Sonnet 5.5 $0.00004 $0.00075
Haiku 4.5 $0.00002 $0.00038

Measured 28d ago against content hash 536f9788bcf2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

review-test 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 28d 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/english-exam-coach/commands/review-test.md · 29 lines

What it actually says

Review a full test: $ARGUMENTS

(A bare placeholder at the end of the line above means nothing filled it in: the request is what the user typed after the command.)

First load the coach. This command is only a shortcut: the instructions and the tools live in this plugin's skill named english-exam-coach (listed as english-exam-coach:english-exam-coach where skills carry their plugin's name). Load that skill now — it is a different thing from this command. If it cannot be loaded here, read ${CLAUDE_PLUGIN_ROOT}/skills/english-exam-coach/SKILL.md instead and treat the folder it is in as the skill folder. Do not search the disk for the skill, and do not improvise the workflow from memory: if neither works, say so and stop. (Once loaded, the skill says how to find its own scripts.)

Then follow the skill's references/test-review.md from the top: find out what material there is, log the scores as the test gave them with coach log-test, collect every mistake into a batch with tags from the closed list, import it with coach log-error --batch, and build the review with coach tests --test. If this is someone else's test, work in tutor mode (--learner <name>). Never fill a gap in the evidence with a guess, and never keep the records in files of your own making — the coach commands are the record.

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. 28d ago Changed · +3 lines 536f9788bcf2
  2. 1mo ago First seen · 26 lines · 21 tokens per session scan A aab9aa0f0636

Subscribe to this mod's changes

review-test is a command published in the GitHub repository OleksiiDotsenko/english-exam-coach (10 stars, last pushed 29d ago), licensed MIT. It adds 21 tokens to every session and 376 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-08.

Analytics and metricsClaude CodeLearning and teachingagent-skillscefrclaude-pluginenglish-learningexam-preparation
Related

review-test compared with commands from other repositories

review-test next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
review-testOleksiiDotsenko/english-exam-coachCommand1029d agoMITA21Claude Code
learnkirilxd/claude-tutorCommand1493mo agoMITA20Claude Code
quizkirilxd/claude-tutorCommand1493mo agoMITA16Claude Code
resourceskirilxd/claude-tutorCommand1493mo agoMITA16Claude Code
reviewkirilxd/claude-tutorCommand1493mo agoMITA16Claude Code
reviewemanzurv/quiz-me-skillCommand52mo agoMITA23Claude Code
interviewsoheilfallah/jobxhunterCommand92mo agoMITA23Claude Code