start-prep

start-prep is a command for Claude Code from OleksiiDotsenko/english-exam-coach. It costs 16 tokens per session (910 once invoked), scanned A, original, MIT.

A guided command for starting exam practice by choosing an exam, level, and section. It supports returning learners by checking saved progress and can store practice history.

In plain words
What is it for?
Use it to begin or resume practice for exams such as IELTS, with progress tracking.
Why use it?
It replaces an unclear first step with short questions and helps learners continue from earlier sessions.

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 — 8 skills, 6 commands shipped together

Good fit Use it to begin or resume practice for exams such as IELTS, with progress tracking.

Compare 6 commands from other repositories ↓
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 8 skills, 6 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 start-prep

README.md
[![agentmods](https://agentmods.dev/badge/commands/oleksiidotsenko/english-exam-coach/start-prep/github.svg)](https://agentmods.dev/commands/oleksiidotsenko/english-exam-coach/start-prep)
Your own site
<a href="https://agentmods.dev/commands/oleksiidotsenko/english-exam-coach/start-prep"><img src="https://agentmods.dev/badge/commands/oleksiidotsenko/english-exam-coach/start-prep/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 start-prep

Your own site · 80×15
<a href="https://agentmods.dev/commands/oleksiidotsenko/english-exam-coach/start-prep"><img src="https://agentmods.dev/badge/commands/oleksiidotsenko/english-exam-coach/start-prep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 910 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 $0.00016 $0.00910
Opus 5 $0.00008 $0.00455
Sonnet 5 $0.00003 $0.00182
Haiku 4.5 $0.00002 $0.00091

Measured 10d ago against content hash ebc503a30465, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

start-prep 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 10d 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/start-prep.md · 65 lines

What it actually says

Start a guided exam-prep session: $ARGUMENTS

Walk the user from zero to a running practice task. Ask ONE question at a time, keep each question short, and skip any question already answered by the arguments or the conversation.

  1. Returning learner check. Run python3 "${CLAUDE_PLUGIN_ROOT}/skills/progress-tracker/scripts/build_report.py" --scope all --no-write (ignore errors if the log does not exist yet; on Windows, if python3 isn't found, use python or py). If there is history, open with a one-line status — last session date, current weakest task type — and offer "pick up where you left off" (drill the weakest task type) as the first option before asking anything else.

  2. Progress storage (first-time setup). If step 1 found no history, this is a fresh learner: mention that progress is saved to ~/english-exam-coach/ by default, and offer a custom location — set the EXAM_COACH_HOME environment variable to any folder (e.g. an Obsidian vault) to keep the log there instead. Settle this before the first attempt is logged. Skip silently for returning learners.

  3. Exam. Ask which exam they are preparing for: IELTS Academic (ielts-academic), IELTS General Training (ielts-general), TOEFL iBT (toefl-ibt), or a CEFR-level exam: B1 (cefr-b1), B2 (cefr-b2), C1 (cefr-c1), C2 (cefr-c2). If they are unsure which exam they need, ask what it is for (university, migration, work, general proof of level) and recommend one, using the exam-router skill's knowledge.

  4. Level and target. For cefr-* exams the level is implied — skip the level question. For IELTS/TOEFL ask for their current working level (B1/B2/C1/C2); if they do not know, offer the 15-minute diagnostic (/assess-level) and use its result. Also ask what score they need and when they sit the exam, then save it once so every later session can be specific about the gap:

    python3 "${CLAUDE_PLUGIN_ROOT}/skills/progress-tracker/scripts/profile.py" set \
      --exam <exam-id> --target-score <score> --exam-date <YYYY-MM-DD> \
      --current-level <CEFR>
    

    Omit any flag they cannot answer — a partial profile is fine, and the command prints the target translated into CEFR. If they do not have a target or a date, skip this and do not ask twice.

  5. Section. Ask what to work on: Writing, Speaking, Reading / Use of English, Listening, or Vocabulary — or a full timed section (point to /mock-exam <exam-id> <section>) or a week-by-week plan toward an exam date (hand off to the study-planner skill).

  6. Mode. Ask whether they want to (a) practice a new task, (b) get feedback on something they already wrote or recorded, or (c) first see how the section works — for (c), explain the format from ${CLAUDE_PLUGIN_ROOT}/data/exam-formats/<exam-id>.md, then offer (a).

  7. Hand off. Route to the matching skill via the exam-router skill (writing-evaluator, speaking-coach, reading-use-of-english, listening-trainer, or vocabulary-builder) with the chosen exam, level, and task type. The skill generates or evaluates, scores, and logs the attempt as usual; scores are indicative self-practice estimates.

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. 10d ago First seen · 65 lines · 16 tokens per session scan A ebc503a30465

Subscribe to this mod's changes

start-prep is a command published in the GitHub repository OleksiiDotsenko/english-exam-coach (8 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 910 once invoked, about $0.0001 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.