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.
git clone --depth 1 https://github.com/xiaolai/claude-english-buddy-for-claudeWrote 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.
[](https://agentmods.dev/commands/xiaolai/claude-english-buddy-for-claude/preview)<a href="https://agentmods.dev/commands/xiaolai/claude-english-buddy-for-claude/preview"><img src="https://agentmods.dev/badge/commands/xiaolai/claude-english-buddy-for-claude/preview/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.
<a href="https://agentmods.dev/commands/xiaolai/claude-english-buddy-for-claude/preview"><img src="https://agentmods.dev/badge/commands/xiaolai/claude-english-buddy-for-claude/preview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00165 | $0.00688 |
| Opus 5 | $0.00082 | $0.00344 |
| Sonnet 5 | $0.00033 | $0.00138 |
| Haiku 4.5 | $0.00016 | $0.00069 |
Grade A, and why
preview 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.
What it actually says
User Input
$ARGUMENTS
Workflow
Step 1: Resolve input
| Input | Action |
|---|---|
| Inline text | Use directly |
| (empty) | Ask for text via AskUserQuestion |
| File path | Read the file |
Step 2: Load resolved config
Load the resolved config per commands/shared/config-loader.md. If auto_correct is false, note this in the report — preview still runs regardless.
Step 3: Dry-run review
This is a dry run. Do NOT:
- Log anything to the JSONL history.
- Submit the corrected text anywhere.
- Trigger the UserPromptSubmit hook.
Dispatch the writing-reviewer agent via the Task tool with the input text. The orchestrator will fan out to grammar-checker, tone-calibrator, and clarity-enhancer as usual.
Step 4: Report
Use the writing-reviewer's output verbatim, but prepend a preview banner and append a "what would change" diff.
# Preview — Dry Run
**Auto-correct is currently**: {enabled / disabled}
**This preview does NOT log, submit, or modify any history.**
---
{writing-reviewer output verbatim}
---
## What Would Change If You Submitted
| Aspect | Before | After |
|--------|--------|-------|
| Prompt length | {n chars} | {n chars} |
| Error count | {n} | 0 |
| Tone score | {1–5} | {1–5} |
## Recommendation
{If Errors found == 0 AND Tone score >= 4: "Ready to submit — no changes needed."}
{If Errors found > 0 OR Tone score <= 3: "Consider applying the corrections above before submitting."}
{If the text is a commit message (single short imperative line): add a commit-specific note with the ≤72 char check.}
Notes
- This command is purely informational; it never mutates state.
- If the input is shorter than 10 characters, skip the review and respond: "Input too short to preview."
- If the input starts with a slash command, skip and respond: "Preview does not apply to slash commands."
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.
- 3d ago First seen · 86 lines · 165 tokens per session scan A d88979d4f136
preview is a command published in the GitHub repository xiaolai/claude-english-buddy-for-claude (29 stars, last pushed 18d ago), licensed ISC. It adds 165 tokens to every session and 688 once invoked, about $0.0008 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 2026-09-08.
Other commands, from other repositories
cancel-ralph
Cancel active Ralph Loop.
obsidian-recap
Summarize a time period from the vault - today, week, or month.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
superpowers-execute
Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.