What is claude-english-buddy-for-claude AGENTS.md?

An English language coach for people using Claude Code who are not native English speakers. It automatically corrects prompts, records recurring mistakes, and provides reports, reviews, and practice exercises.

Use it to correct prompts, review writing, inspect daily or long-term error trends, preview changes, and practise common mistakes with quizzes.

It helps users notice repeated English errors and turn them into lessons instead of receiving only a one-time correction.

How xiaolai/claude-english-buddy-for-claude configures Claude Code and

Reuse

Borrowing it

Nothing to install: this file belongs to xiaolai/claude-english-buddy-for-claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/xiaolai/claude-english-buddy-for-claude/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/xiaolai/claude-english-buddy-for-claude

Made for: Claude Code, Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/xiaolai/claude-english-buddy-for-claude/agents-md/github.svg)](https://agentmods.dev/instructions/xiaolai/claude-english-buddy-for-claude/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/xiaolai/claude-english-buddy-for-claude/agents-md"><img src="https://agentmods.dev/badge/instructions/xiaolai/claude-english-buddy-for-claude/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/xiaolai/claude-english-buddy-for-claude/agents-md"><img src="https://agentmods.dev/badge/instructions/xiaolai/claude-english-buddy-for-claude/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,208 This file is loaded in full into every session.

When invoked 1,208 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01208	$0.01208
Opus 5.5	$0.00483	$0.00483
Sonnet 5.5	$0.00242	$0.00242
Haiku 4.5	$0.00121	$0.00121

Measured 1mo ago against content hash 399dce42993e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-english-buddy-for-claude AGENTS.md 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 1mo 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.

AGENTS.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

claude-english-buddy

English language coach for non-native speakers using Claude Code or Codex CLI. Auto-corrects prompts via UserPromptSubmit hook, tracks corrections, generates daily reports.

The plugin ships two layouts from one repo: .claude-plugin/ + commands/ + agents/ + skills/ for Claude Code, and .codex-plugin/ + codex/skills/ for Codex. Both hosts load the same hooks/hooks.json and scripts/. The Codex tree is hand-built; read codex/AGENTS.md before changing it, and never regenerate it with build-codex.mjs --force.

Prerequisites

Node.js >= 18
No npm dependencies; npm test runs the Node.js native test runner directly.

Project structure

commands/
  today.md              /today — daily correction report with lessons
  stats.md              /stats — long-term trends and improvement
  mistakes.md           /mistakes — all-time recurring errors
  config.md             /config — configure settings
  review.md             /review — deep text review
  preview.md            /preview — dry-run correction preview
  drill.md              /drill — spot-quiz on top recurring mistakes
  shared/
    config-loader.md    Shared partial — resolve merged config
    jsonl-parser.md     Shared partial — read JSONL history
    format-report.md    Shared partial — report output conventions
agents/
  writing-reviewer.md   Deep English text reviewer — orchestrator
  grammar-checker.md    Grammar and mechanics subagent
  tone-calibrator.md    Tone and register subagent
  clarity-enhancer.md   Clarity and phrasing subagent
skills/
  claude-english-buddy/
    writing-guide/              SKILL.md — meta-router to focused skills
    grammar-fundamentals/       Grammar rules reference
    punctuation-rules/          Punctuation rules reference
    tone-calibration/           Tone and register guidance
    technical-writing/          Conventions for dev-facing prose
    common-non-native-mistakes/ Common L2-English error patterns
.claude/
  rules/
    01-voice-preservation.md    Preserve author voice during corrections
    02-minimal-invasiveness.md  Only change text tied to an identified error
    03-no-over-polishing.md     Cap lessons per review; no cosmetic rewrites
hooks/
  hooks.json            UserPromptSubmit + SessionEnd hooks
scripts/
  prompt-coach-hook.mjs   Main hook — correct/translate/refine
  session-end-hook.mjs    Session summary on exit
  history-report.mjs      History reports as JSON for the Codex skills (--host codex)
  lib/
    detect.mjs          Language detection (ASCII ratio heuristic)
    state.mjs           Correction history (JSONL per day)
    stats.mjs           Trend analysis and pattern extraction
tests/
  detect.test.mjs       Language detection tests
  state.test.mjs        State persistence tests
  stats.test.mjs        Stats computation tests
  annotations.test.mjs  Annotation parser tests
  hook-output.test.mjs  Hook wire format, run as a real process
  history-report.test.mjs  history-report.mjs CLI, run as a real process
  codex-layout.test.mjs Codex layout invariants
.codex-plugin/
  plugin.json           Codex manifest (skills: ./codex/skills/)
codex/
  AGENTS.md             Codex layout notes: paths, hooks, differences from Claude Code
  skills/               17 hand-built Codex skills, prefixed claude-english-buddy-
package.json            Node.js project config

Read the full file on GitHub · 106 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.

1mo ago Changed · +16 lines · +403 tokens per session 399dce42993e
1mo ago First seen · 90 lines · 805 tokens per session scan A 1529adf5e3f7

Subscribe to this mod's changes

claude-english-buddy-for-claude AGENTS.md is an instructions file published in the GitHub repository xiaolai/claude-english-buddy-for-claude (30 stars, last pushed 1mo ago), licensed ISC. It adds 1,208 tokens to every session, about $0.0048 per session on Opus 5.5. 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 2026-09-30.

Learning and teaching Writing and docs

claude-english-buddy-for-claude AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-english-buddy-for-claude AGENTS.mdxiaolai/claude-english-buddy-for-claude	Instructions file	30	1mo ago	ISC	A	1,208	Claude Code, Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

claude-english-buddy-for-claude: Instructions file for Claude Code