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/progress-tracker)<a href="https://agentmods.dev/skills/oleksiidotsenko/english-exam-coach/progress-tracker"><img src="https://agentmods.dev/badge/skills/oleksiidotsenko/english-exam-coach/progress-tracker/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/progress-tracker"><img src="https://agentmods.dev/badge/skills/oleksiidotsenko/english-exam-coach/progress-tracker.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 | $0.00108 | $0.01665 |
| Opus 5 | $0.00054 | $0.00833 |
| Sonnet 5 | $0.00022 | $0.00333 |
| Haiku 4.5 | $0.00011 | $0.00167 |
Grade A, and why
progress-tracker 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.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Progress Tracker
Two-layer model: attempts.jsonl is the append-only source of truth;
Markdown reports in reports/ are derived and regenerable. Scripts live at
${CLAUDE_PLUGIN_ROOT}/skills/progress-tracker/scripts/ (if the variable is
unset, resolve relative to this SKILL.md).
The base directory is resolved by the scripts themselves:
--base flag → $EXAM_COACH_HOME → ~/english-exam-coach/. Because
attempts are usually logged inline by another skill — which silently creates
~/english-exam-coach/ on first write — the default-vs-custom choice must be
surfaced at the first real entry point (/start-prep, or exam-router before
its diagnostic) before any attempt is logged: ask once whether the user
wants the default (~/english-exam-coach/) or a custom path such as an
Obsidian vault folder, then suggest exporting EXAM_COACH_HOME in their
shell profile to persist the choice. If this skill is nonetheless the first
to log and no base exists yet, ask that same question before the first write.
When to use
- After ANY task is scored by another skill → log the attempt, silently.
- When the user asks for results, trends, streaks, or weakest areas → build and show a report.
- When advice needs the learner's target ("am I on track?", "is B2 enough?") → read the profile; when they state a target or an exam date → save it.
The learning loop
Scores alone are amnesia: every session grades, explains, and forgets. The
loop turns each mistake into a scheduled re-test on a freshly generated item.
The full protocol — two-pass judging, the error taxonomy, the queue, and the
revise-and-resubmit cycle — is in
references/the-loop.md. Read it when scoring
anything or when asked what to practise next.
python3 ".../scripts/log_error.py" --category <cat> --subtype <sub> \
--point "<the specific, re-testable target>" # one line per mistake
python3 ".../scripts/queue.py" sync # fold new points in
python3 ".../scripts/queue.py" due # what is due today
python3 ".../scripts/drill_context.py" # ONE explainable next step
python3 ".../scripts/state.py" validate # check the directory is sound
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/tagging-examples.md 4.7 KB
- references/the-loop.md 5.8 KB
- scripts/build_report.py 28 KB runs code
- scripts/convert_score.py 6.5 KB runs code
- scripts/drill_context.py 7.2 KB runs code
- scripts/log_attempt.py 12 KB runs code
- scripts/log_error.py 8.9 KB runs code
- scripts/profile.py 7.5 KB runs code
- scripts/queue.py 9.3 KB runs code
- scripts/state.py 9.4 KB runs code
- scripts/timed_speak.py 7.9 KB runs code
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 · 137 lines · 108 tokens per session scan A 7f6f76a00e4c
progress-tracker is a skill published in the GitHub repository OleksiiDotsenko/english-exam-coach (8 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 1,665 once invoked, about $0.0005 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.