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 agentmods add skills/m98/fluent/fluent-reviewnpx skills add m98/fluent --skill fluent-reviewgit clone --depth 1 https://github.com/m98/fluentWhat 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 | $0.00079 | $0.01777 |
| Opus 5 | $0.00039 | $0.00889 |
| Sonnet 5 | $0.00016 | $0.00355 |
| Haiku 4.5 | $0.00008 | $0.00178 |
Grade A, and why
fluent-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spaced-Repetition Review Session
Overview
Replay items the learner learned before, timed so they hit just before the forgetting curve drops them. This is the single most effective session type — the system depends on it running daily. Items the learner gets right get pushed further into the future; items they miss come back tomorrow.
When to Use
Trigger this skill only when the learner types /fluent-review. The skill is gated with disable-model-invocation: true — mutating SM-2 state from a misread prompt would cascade through every future session.
Skip this skill when the queue is empty — suggest /fluent-vocab or /fluent-learn instead.
Instructions
1. Load review queue
python3 "${CLAUDE_PLUGIN_ROOT:-${CLAUDE_PROJECT_DIR:-.}}/.claude/hooks/read-db.py"
Read spaced-repetition.review_queue.today and daily_limits.review_items_per_day. Sort items by priority (critical → high → medium → low). Cap at the daily limit (usually 20).
If the queue is empty:
🎉 No reviews due today! Your spaced repetition is up to date.
Want to practice something new? Try:
- `/fluent-learn` — adaptive mixed practice
- `/fluent-vocab` — learn new words
- `/fluent-progress` — see your stats
2. Opening
# 🔄 Today's Spaced Repetition Review
Hallo {name}! Time to review items your brain is about to forget. This keeps everything fresh. 🧠
**Items Due Today:** {count}
**Estimated Time:** ~{minutes} min
Why review? Spaced repetition prevents forgetting, moves items into long-term memory, and builds automaticity.
**Ready? Let's start!** 💪
3. Generate exercise per item
Each item has:
{
"item_id": "...",
"item_type": "error_pattern | vocabulary | grammar_rule",
"easiness_factor": 2.5,
"interval_days": 6,
"repetitions": 2,
"due_date": "YYYY-MM-DD",
"priority": "critical | high | medium | low",
"content": "...",
"answer": "..."
}
Generate an exercise matched to item_type:
- error_pattern: load the pattern from
mistakes-db, create a scenario that forces the correct form. E.g.formal_informal_confusion→ ask the learner to complete a formal email opening. - vocabulary: recognition (target → native), production (native → target), or cloze — rotate modes.
- grammar_rule: a fill-in or error-correction exercise that tests the rule.
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.
- 3d ago First seen · 222 lines · 79 tokens per session scan A da732f1d90b7
fluent-review is a skill published in the GitHub repository m98/fluent (387 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 1,777 once invoked, about $0.0004 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
trulens-notebook-execution
Execute and display Jupyter notebooks for TruLens demos and quickstarts.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
master-yinguang
Use when user asks about 印光大师, 净土, 念佛, 持名念佛, 十念法, 摄耳谛听, 老实念佛, 信愿行, 带业往生, 仗佛慈力, 自力他力, 竖出横超, 往生, 极乐, 阿弥陀佛, 净土三经, 敦伦尽分, 闲邪存诚, 因果报应, 文钞, 一函遍复, or wants teaching in 印光大师 Yinguang's voice. Triggers include "印光"、"文钞"、"老实念佛"、"信愿行"、"带业往生"、"仗佛慈力"、"横超竖出"、"都摄六根"、"净念相继"、"敦伦尽分"、"闲邪存诚"、"因果"、"十念法"、"摄耳谛听"、"一函遍复"、"净土三经"、"往生" — invoke…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
obsidian-to-clew-import
Convert an Obsidian vault or wiki-linked markdown graph into a validated structured-learning graph package for Clew. Use when the user wants to inspect a vault, preview whether it imports cleanly, preserve explicit relation markers, choose only the few import settings that matter, and produce a fail-closed package…