agentleFS
Sign inStart free
remenoscodesremenoscodes/claude-language-coach/AGENTS.md

claude-language-coach

AGENTS.md0 starsChanged 9 months agoMITView on GitHub

Claude Code plugin for ambient language coaching during coding sessions. Supports 8 languages with grammar corrections, vocabulary, pronunciation, and SM-2 spaced repetition. Inherits workspace conventions from ~/AGENTS.md.

The file

Create a free account to mount
Files
AGENTS.md

claude-language-coach

Claude Code plugin for ambient language coaching during coding sessions. Supports 8 languages with grammar corrections, vocabulary, pronunciation, and SM-2 spaced repetition.

Inherits workspace conventions from ~/AGENTS.md.

Status

  • Version: 1.10.0
  • State: active
  • Deploy: Claude Code plugin via remenoscodes/claude-plugin-marketplace

Stack

Claude Code plugin system: CLAUDE.md instructions, shell hooks (Bash), Markdown skills. Memory: JSON files at ~/.claude/coaching/ with auto-generated MD companions.

Key Commands

/claude-language-coach:setup          # Interactive setup (writes config + instructions to CLAUDE.md)
/claude-language-coach:lang en        # Session review for English
/claude-language-coach:lang all       # Session review for all languages
/claude-language-coach:progress       # Longitudinal progress report (all languages)
/claude-language-coach:progress es    # Progress report for a specific language
claude --plugin-dir ./                # Local development (test without installing)

Architecture

  • hooks/coaching-nudge.sh — UserPromptSubmit hook injecting a nudge on every prompt
  • skills/ — Four skills: language-coaching (reference, 500+ lines), lang (on-demand review), progress (longitudinal analytics), setup (interactive config)
  • Three-layer design: CLAUDE.md config (~80 lines, always in context) + hook (reinforcement) + skill (detailed reference on demand)
  • Dual-file memory: {lang}-coaching.json (source of truth) + {lang}-coaching.md (human-readable, auto-regenerated)
  • SRS via SM-2: correction sets next_review to tomorrow, correct usage grows interval, mastery at 21d + 5 correct

Related Projects

  • ~/source/remenoscodes.claude-plugin-marketplace — Central marketplace distributing this plugin
  • ~/source/remenoscodes.launchpad — Launch strategy (campaign: claude-language-coach/)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free