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.
/plugin marketplace add OleksiiDotsenko/english-exam-coach/plugin install english-exam-coachWrote 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.
[](https://agentmods.dev/commands/oleksiidotsenko/english-exam-coach/start-prep)<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.
<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>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.
| Model | Per session | Once 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 |
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.
What it actually says
Start a guided exam-prep session: $ARGUMENTS
Walk the user from zero to a running practice task. Ask ONE question at a time, keep each question short, and skip any question already answered by the arguments or the conversation.
-
Returning learner check. Run
python3 "${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, ifpython3isn't found, usepythonorpy). 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. -
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 theEXAM_COACH_HOMEenvironment 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. -
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 theexam-routerskill's knowledge. -
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.
-
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 thestudy-plannerskill). -
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). -
Hand off. Route to the matching skill via the
exam-routerskill (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.
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.
- 10d ago First seen · 65 lines · 16 tokens per session scan A ebc503a30465
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.
Other commands, from other repositories
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
learn
Start learning a new topic — asks clarifying questions, researches resources, and creates a structured learning plan.
quiz
Quiz yourself on a topic from your learning plan with adaptive difficulty and mixed question formats.
resources
Find curated learning resources — books, courses, tutorials, and docs for any topic.
review
View your learning progress — quiz scores, weak areas, and what to study next.
interview
Prepare for the interview from the filed application — predicted questions, STAR answers from real evidence, and gap-defence.