fluent-feedback-formatter

A shared format for responding to answers in language-learning exercises, including corrections, explanations, a complete correct version, and a score.

In plain words
What is it for?
It is for grading answers in Fluent writing, vocabulary, speaking, reading, learning, and review sessions while labeling mistake categories and severity.
Why use it?
It makes feedback consistent, so learners can recognize mistakes and compare answers across different practice types.

Skill for Claude CodeCodex

Part of the fluent plugin — 12 skills, 4 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/m98/fluent/fluent-feedback-formatter
Any agent
npx skills add m98/fluent --skill fluent-feedback-formatter
Clone the repo
git clone --depth 1 https://github.com/m98/fluent

Made for: Claude Code, Codex.

Or install fluent, the plugin that ships this one along with the rest of its 12 skills, 4 hooks.

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,123 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00091 $0.01123
Opus 5 $0.00046 $0.00562
Sonnet 5 $0.00018 $0.00225
Haiku 4.5 $0.00009 $0.00112

Measured 3d ago against content hash fb9a2b23292e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fluent-feedback-formatter 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.

.claude/skills/fluent-feedback-formatter/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feedback Formatter

Overview

Every practice session ends each turn with immediate feedback. Consistency matters — the learner builds mental models from the structure, and error patterns we mine from session files depend on predictable markers (❌, ✅, severity emoji). This skill defines the single feedback shape used across all Fluent practice skills.

When to Use

Load this skill whenever the tutor:

  • Grades a learner answer in any practice skill (fluent-learn, fluent-vocab, fluent-writing, fluent-speaking, fluent-reading, fluent-review).
  • Needs to classify an error by severity before writing to mistakes-db.json.
  • Needs to tag an error by category (grammar, vocabulary, prepositions, etc.).

Skip this skill for non-feedback output (greetings, summaries, progress reports).

Instructions

1. Standard template

{✅ or ❌} {one-line encouragement or gentle correction}

**Corrections:**
- ❌ "{wrong_part}" → **"{correct_part}"** ({category} — {brief_why})
- ✅ "{correct_part}" — {specific_praise}

**Correct version:**
"{full_correct_sentence}"

**Score: {X}/10** {emoji} {short_comment}

---

Skip the ❌ block if the answer is fully correct. Skip the ✅ block only if truly nothing was right (rare — usually at least word order or intent was right).

2. Tag severity on every error

Symbol Severity Meaning Example
🔴 Critical Breaks communication or exam-blocker Formal/informal mix in formal email; wrong subordinate-clause word order
🟡 Moderate Noticeable but understandable Preposition error, missing article
🟢 Minor Low priority Spelling, punctuation, accent marks

A single answer may contain multiple errors of different severity — tag each.

3. Use these category labels

These feed mistakes-db.json:

  • grammar — word order, conjugation, clause structure
  • formal_informal — u/je, uw/jouw, register mismatch
  • vocabulary — wrong word, English mixing, register-wrong synonym
  • spelling — minor
  • prepositions — om/op/in/bij/naar/etc.
  • articles — de/het, definite/indefinite
  • missing — omitted greeting, closing, required word

Read the full file on GitHub · 99 lines

Changes

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.

  1. 3d ago First seen · 99 lines · 91 tokens per session scan A fb9a2b23292e

Subscribe to this mod's changes

fluent-feedback-formatter is a skill published in the GitHub repository m98/fluent (387 stars, last pushed 2mo ago), licensed MIT. It adds 91 tokens to every session and 1,123 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

trulens-notebook-execution

Execute and display Jupyter notebooks for TruLens demos and quickstarts.

truera/trulens · 21 tokens

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.

companion-inc/feynman · 63 tokens

deck-course-module

暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.

nexu-io/html-anything · 25 tokens

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…

xr843/Master-skill · 274 tokens

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…

dzhng/skills · 162 tokens

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…

miuuyy/Clew · 72 tokens