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-speakingnpx skills add m98/fluent --skill fluent-speakinggit 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 | $0.00076 | $0.01652 |
| Opus 5 | $0.00038 | $0.00826 |
| Sonnet 5 | $0.00015 | $0.00330 |
| Haiku 4.5 | $0.00008 | $0.00165 |
Grade A, and why
fluent-speaking scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Speaking Practice (Typed)
Overview
Conversational practice through typed dialogue. Unlike /fluent-writing, prioritize communication and naturalness — grammar errors that don't block meaning are downplayed. Goal: build the learner's confidence to produce target-language output without over-analyzing.
When to Use
Trigger this skill only when the learner types /fluent-speaking. The skill is gated with disable-model-invocation: true — 15-20 min interactive session with DB writes should never start from an ambiguous prompt.
Skip this skill below A1 mastery 2 — the learner needs a basic word bank and verb conjugations first (run /fluent-vocab a few times).
Instructions
1. Load context
python3 "${CLAUDE_PLUGIN_ROOT:-${CLAUDE_PROJECT_DIR:-.}}/.claude/hooks/read-db.py"
Need: learner-profile (level, target language), mastery-db.skills_mastery.speaking.
2. Opening
# 🗣️ {target_language} Speaking Practice
Hallo {name}!
Today we're practicing **speaking** through typed conversation. I'll ask you questions or give scenarios, you respond naturally in {target_language} — just like a real conversation.
**Focus:** natural expression, fluency, pronunciation (typed)
**Level:** {CEFR}
**Duration:** 15-20 min
**Tips:**
- Think in {target_language}, not {native_language}
- Don't chase perfect grammar — focus on getting your message across
- Use complete sentences
- Be natural and conversational
**Ready? Let's chat!** 💬
3. Pick topic based on mastery
A2 topics:
- Personal introductions
- Daily routine
- Hobbies and interests
- Shopping
- Making appointments
- Asking for directions
- Ordering food
- Talking about weather
- Weekend plans
- Work / study
B1+: opinions, comparisons, hypotheticals, complaints, narratives.
4. One question at a time
## Question {N}: {Topic}
{Question in target language}
**Type your answer in {target_language}:**
Build the conversation naturally — after 3-4 Qs on one topic, transition: Interessant! Let's talk about something else....
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 · 235 lines · 76 tokens per session scan A 52768aa526a3
fluent-speaking is a skill published in the GitHub repository m98/fluent (387 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 1,652 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.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.