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/skills/oleksiidotsenko/english-exam-coach/speaking-coach)<a href="https://agentmods.dev/skills/oleksiidotsenko/english-exam-coach/speaking-coach"><img src="https://agentmods.dev/badge/skills/oleksiidotsenko/english-exam-coach/speaking-coach/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/skills/oleksiidotsenko/english-exam-coach/speaking-coach"><img src="https://agentmods.dev/badge/skills/oleksiidotsenko/english-exam-coach/speaking-coach.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 | $0.00117 | $0.01716 |
| Opus 5 | $0.00059 | $0.00858 |
| Sonnet 5 | $0.00023 | $0.00343 |
| Haiku 4.5 | $0.00012 | $0.00172 |
Grade A, and why
speaking-coach 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Speaking Coach
Terminal-friendly speaking practice: record or perform → transcribe →
evaluate. Paths are relative to ${CLAUDE_PLUGIN_ROOT} (if unset, resolve
relative to the plugin root — the directory two levels above this file,
.../plugins/english-exam-coach).
When to use
The user wants a speaking task, mock speaking interview, or feedback on an answer they spoke (pasted as transcript or provided as an audio file).
Steps
-
Identify exam + level + part. Load
data/exam-formats/<exam-id>.md,data/cefr/speaking-descriptors.md, anddata/cefr/speaking-calibration-anchors.md(leveled transcript samples). Seed shapes:data/item-bank/seed/speaking-tasks.md(imitate format, never reuse). -
Generate the task with the exam's real prep/speaking times (e.g. IELTS Part 2: 1 min prep, 1–2 min talk; TOEFL interview answers: 45 s each with no preparation time). Pitch the prompt's demand to the level (B1 concrete/personal; B2 opinion on a familiar topic; C1 abstract, asks the speaker to weigh/hypothesise; C2 nuanced) —
speaking-calibration- anchors.mdshows an at-level answer to aim the prompt at. Visual-dependent tasks (Cambridge B1 Part 2 describe-a-photo; B2 First / C1 Advanced Part 2 compare-photographs; C2 Part 2 picture discussion) can't be rendered here; say so and offer a non-visual part instead of faking it. IELTS Speaking uses no visual prompts — its Part 2 is a text cue card and IS fully renderable. The two TOEFL 2026 speaking tasks are single-scenario tasks — generate them as one whole, never as a list of unrelated items:- Listen and Repeat — one scenario for all 7 sentences (a library orientation, a campus tour, step-by-step directions), introduced by a short line that is read but not repeated. Sentences grow from ~5–6 words to the upper teens.
- Take an Interview — open with a brief scenario ("you have agreed to
take part in a study about…"), then 4 questions on that one everyday
topic: concrete → past experience → opinion → hypothetical. 45 s each is
about 90–130 words.
See
data/item-bank/seed/speaking-tasks.mdfor worked examples of both. Tell the user how to respond, in order of preference: - record themselves (any voice recorder) and paste an accurate transcript, noting hesitations/self-corrections honestly;
- or speak first and then type from memory (say that this loses fluency information);
- for a paired-format task (collaborative discussion), play the partner: alternate short turns with the user in chat.
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.
- 12d ago First seen · 125 lines · 117 tokens per session scan A 94477b7a068c
speaking-coach is a skill published in the GitHub repository OleksiiDotsenko/english-exam-coach (8 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 1,716 once invoked, about $0.0006 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 skills, from other repositories
oral-english-practice
A Claude Code skill that stores and analyses spoken-English practice completed in the Claude app. The app handles the conversation; this skill keeps reports, scores, mistakes, progress trends, and the next practice focus.
language-coach
Language coaching for every prompt. Use when the user runs /language-coach with any sub-command (setup, native, target, style, response, goal, mode, focus, band, level, status, off, on). Routes to the correct action based on the argument provided.
language-review
Analyze language learning progress from local data. Use when the user runs /language-coach:language-review or asks to review their progress, see their band history, check improvement trends, or analyze their IELTS score data.
learning-and-development
Builds capability — skills gaps, career frameworks, training that transfers to the job, and internal mobility. Use this to design a career ladder, close a capability gap, decide whether to build or hire a skill, structure onboarding into a role, or work out why training keeps failing to change anything.
diagnose
A short question-based assessment of a pilot's current skill level. It produces a profile and saves it in the connected browser or database.
lesson-close
A workflow for finishing the day's lesson file, recording its status and duration, then saving it to the personal-guide GitHub repository.