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-writingnpx skills add m98/fluent --skill fluent-writinggit 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 | $0.01835 |
| Opus 5 | $0.00038 | $0.00918 |
| Sonnet 5 | $0.00015 | $0.00367 |
| Haiku 4.5 | $0.00008 | $0.00184 |
Grade A, and why
fluent-writing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Practice Session
Overview
Full-text writing practice with systematic correction. One scenario per session, detailed feedback broken down by severity and category, DB update at end. Mastery-driven scenario selection keeps the task at the right level — challenging, not frustrating.
When to Use
Trigger this skill only when the learner types /fluent-writing. The skill is gated with disable-model-invocation: true — a 15-20 min interactive session with DB writes should never start from an ambiguous prompt.
Skip this skill in favor of /fluent-vocab if the learner has not yet hit mastery 2 in basic vocabulary — writing needs a minimum word bank.
Instructions
1. Load context
python3 "${CLAUDE_PLUGIN_ROOT:-${CLAUDE_PROJECT_DIR:-.}}/.claude/hooks/read-db.py"
Need: learner-profile (level, target language, focus areas), mistakes-db (weak writing patterns), mastery-db (writing sub-skills).
2. Pick scenario type
From mastery-db.skills_mastery:
- Formal email (if
writing_formal_emailmastery < 4) - Informal email (if
writing_informal_email< 4) - Form filling (if
writing_forms< 4) - Newsletter / personal text (if overall writing < 3)
- Mixed scenarios (if all ≥ 4)
Scenarios must match the learner's CEFR level — A2 uses everyday situations, B1+ adds opinion / complaint / inquiry.
3. Present the task
## ✍️ Writing Exercise
**Scenario:** {clear description in native language}
**Task:** Write a {type} in {target_language}.
**Requirements:**
- Length: {X-Y} words
- Include: {must-include elements}
- Register: {formal / informal}
- Level: {CEFR}
{Optional: example structure for harder tasks}
**Write your {text_type} below:**
4. Wait for the full text
Don't correct mid-composition. Let the learner finish.
5. Systematic error analysis
Check every sentence for these categories:
- Grammar — word order, conjugation, clause structure, articles
- Formal/informal — register consistency
- Vocabulary — wrong word, English mixing, register-wrong synonyms
- Missing elements — greeting, closing, required fields
- Spelling — minor at A2, weightier at B2+
- Structure — organization, flow, paragraphing
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 · 233 lines · 76 tokens per session scan A 16c6e9be0f89
fluent-writing 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 1,835 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
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.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.