Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add rayw-lab/english-immersion-reader --skill immersion-readergit clone --depth 1 https://github.com/rayw-lab/english-immersion-readerWrote 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/rayw-lab/english-immersion-reader/immersion-reader)<a href="https://agentmods.dev/skills/rayw-lab/english-immersion-reader/immersion-reader"><img src="https://agentmods.dev/badge/skills/rayw-lab/english-immersion-reader/immersion-reader.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.00536 |
| Opus 5 | $0.00015 | $0.00268 |
| Sonnet 5 | $0.00006 | $0.00107 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
immersion-reader 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 8d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Immersion Reader
Setup (run once before first use)
- Locate the repo root: this skill folder lives at
<repo>/skills/immersion-reader/— resolve the real path of this file and go up two directories. If you only have the skill folder (no repo), clone it first:git clone https://github.com/rayw-lab/english-immersion-reader - Install the two Python dependencies (Python >= 3.10):
python3 -m pip install jsonschema edge-tts(or, inside the repo:python3 -m pip install -e .) edge-ttsneeds network access at synthesis time; the script manages proxy env vars itself, so no proxy setup is required.
Follow AGENTS.md in this repository.
Compile flow
- Write
lessons/<slug>/segments.jsonperAGENTS.md(segments + hard + chunks + patterns + transfer task + fulllexicon). python src/tts_generate.py lessons/<slug>/segments.json --out lessons/<slug>/audio— one command produces segment mp3s, per-word audio for every lexicon term (default--word-audio full, so card/selection playback never falls back to browser TTS), and.words.jsonsidecars that power the karaoke word highlight. Needs network.python src/build_page.py lessons/<slug>/segments.json --out lessons/<slug>— validates the contract, injects data + word timings, prints the Chinese closeout block. Relay that block verbatim; do not invent a summary.- Upgrading an older lesson: rerun step 2 (word audio fills in incrementally);
add
--forceto regenerate segment mp3s so they gain timing sidecars.
Use this skill when the user asks for any of these:
- turn an English article URL into an immersion reading lesson
- turn a YouTube video or transcript into an English listening lesson
- build an H5/static HTML lesson with original English text
- create local audio, word cards, chunk cards, dictation, shadowing, or agent-copy prompts from source English
Default output stays local under lessons/; generated lessons and transcripts are not committed unless the user owns the rights and explicitly asks.
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.
- 8d ago First seen · 45 lines · 30 tokens per session scan A da58188a025d
immersion-reader is a skill published in the GitHub repository rayw-lab/english-immersion-reader (26 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 536 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
aha
Explain an expression in the language you're learning that you can't read literally — get a verdict (memorize vs learnable rule) + how to read it, saved to the decode dataset. Usage: /aha [+ your hunch].
tutor
Drill your recorded pains (friction phrasings, grammar fixes, irregular verbs, learned vocab) with spaced repetition. Usage: /tutor [size].
loot
Add words/terms you're learning, enriched (translation, alternative translations, examples, synonyms, definition) into your native/learning languages. Comma-separated for several at once. Usage: /loot [, , ...].
setup
Set up shadowling's three languages — native (translations), learning (what you study), and explanation (corrections). Required before first use. Usage: /shadowling:setup.
debrief
Review your buffered writing into per-category frequency docs (grammar / rephrasings / idioms / verbs). Usage: /debrief.
anki-sync
Push enriched vocab to Anki Desktop as flashcards and pull review progress back. Usage: /anki-sync.