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-learnnpx skills add m98/fluent --skill fluent-learngit 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 | $0.00085 | $0.01861 |
| Opus 5 | $0.00043 | $0.00931 |
| Sonnet 5 | $0.00017 | $0.00372 |
| Haiku 4.5 | $0.00009 | $0.00186 |
Grade A, and why
fluent-learn scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Main Adaptive Learning Session
Overview
The flagship command. Interleaves skills, adapts difficulty per answer, and covers the whole evidence-based loop: active recall → immediate feedback → spaced repetition → tracking. Typically runs 15-20 min, mixing 2-3 patterns to force discrimination.
When to Use
Trigger this skill only when the learner types /fluent-learn. The skill is gated with disable-model-invocation: true — an ambiguous auto-trigger would launch a 20-min interactive session and mutate 6 JSON databases.
Skip this skill the very first time a learner runs the system — route to /fluent-setup instead.
Instructions
1. Load learner context
python3 "${CLAUDE_PLUGIN_ROOT:-${CLAUDE_PROJECT_DIR:-.}}/.claude/hooks/read-db.py"
Need all 6 DBs. If any missing, direct the learner to /fluent-setup and stop.
2. Analyze today's plan
- Streak:
learner-profile.current_streak_days - Due reviews:
computed.due_reviews_count - Weak patterns:
mistakes-db.error_patternswheremastery_level <= 2(descending by frequency) - Recent performance:
progress-db.weekly_summary - Skills not practiced recently: check
mastery-db.skills_mastery.{skill}.last_practiced
3. Greet
# {greeting in target language}, {name}! 👋
**Today's Status:**
- 🔥 Streak: {X} {day/days}
- 📚 Review items due: {Y}
- 🎯 Focus area: {weakest skill or top weak pattern}
- ⭐ Level: {current} → {target} ({progress}%)
**What would you like to practice today?**
1. 📝 Writing (emails, letters, forms)
2. 🗣️ Speaking (typed conversation)
3. 📖 Vocabulary (flashcard drills)
4. 👀 Reading (comprehension)
5. 🔄 Spaced Review (today's due items)
6. 🎲 Surprise me! (adaptive mix)
**Type a number or skill name:**
4. Route
- 1-5 → hand off to the matching skill (
fluent-writing,fluent-speaking,fluent-vocab,fluent-reading,fluent-review). Those skills cover everything needed; this skill's job here is just to dispatch. - 6 (adaptive mix) → use this skill's own exercise sequencer (below).
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.
- 2d ago First seen · 205 lines · 85 tokens per session scan A 2e457fd7986e
fluent-learn is a skill published in the GitHub repository m98/fluent (381 stars, last pushed 2mo ago), licensed MIT. It adds 85 tokens to every session and 1,861 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…