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/mock-exam)<a href="https://agentmods.dev/commands/oleksiidotsenko/english-exam-coach/mock-exam"><img src="https://agentmods.dev/badge/commands/oleksiidotsenko/english-exam-coach/mock-exam/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/mock-exam"><img src="https://agentmods.dev/badge/commands/oleksiidotsenko/english-exam-coach/mock-exam.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 | $0.00017 | $0.00619 |
| Opus 5 | $0.00009 | $0.00309 |
| Sonnet 5 | $0.00003 | $0.00124 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade A, and why
mock-exam 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 11d 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
Run a timed mock exam section: $ARGUMENTS
- Parse the arguments as exam id and section. If either is missing, use the
exam-routerskill to resolve them from the user's goals (or ask once). Valid exam ids: ielts-academic, ielts-general, toefl-ibt, cefr-b1, cefr-b2, cefr-c1, cefr-c2. - Load the exact section format from
${CLAUDE_PLUGIN_ROOT}/data/exam-formats/<exam-id>.mdand announce the rules: parts, item counts, and the real time limit. Note the start time. - Run the section at full length using the matching skill
(reading-use-of-english, writing-evaluator, speaking-coach, or
listening-trainer) with ORIGINAL items only. No hints, no feedback, and
no answer key until the section is finished. Each of those skills already
ends with a single silent auto-log — for a mock, tell the skill to make
that its ONE log, writing under
--session mock-<exam-id>-<date>with the split--secondsfrom step 4. Do not add a second log; one row per task type, in the mock session, with split time. - When the user submits (or declares time up), score the whole section and
give per-part feedback and explanations. The single per-task log is the
delegated skill's own silent auto-log from step 3 (under
--session mock-<exam-id>-<date>, using the canonical--task-typeslugs fromdata/task-types.md) — do not log a separate attempt here. A section runs under ONE clock, so split the real elapsed time across the task types (e.g. proportional to item count) and pass each task's share as the--secondsfor that log — do not log the full section time on every row, or the report's "min on task" will be inflated N-fold.- If the user quits mid-section: offer to score only the fully completed parts and log those task types with the real elapsed time and the same session id. Never fabricate answers for unattempted items. If nothing was completed, log nothing and say so.
- Finish with the session report:
python3 "${CLAUDE_PLUGIN_ROOT}/skills/progress-tracker/scripts/build_report.py" --scope session --session mock-<exam-id>-<date>. (On Windows, ifpython3isn't found, usepythonorpyinstead.)
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.
- 11d ago First seen · 39 lines · 17 tokens per session scan A 534fa50f9869
mock-exam is a command published in the GitHub repository OleksiiDotsenko/english-exam-coach (8 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 619 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.