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 skills add swapii/claude-linguist --skill review-user-prompt-englishgit clone --depth 1 https://github.com/swapii/claude-linguistWrote 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/skills/swapii/claude-linguist/review-user-prompt-english)<a href="https://agentmods.dev/skills/swapii/claude-linguist/review-user-prompt-english"><img src="https://agentmods.dev/badge/skills/swapii/claude-linguist/review-user-prompt-english/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/skills/swapii/claude-linguist/review-user-prompt-english"><img src="https://agentmods.dev/badge/skills/swapii/claude-linguist/review-user-prompt-english.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 | $0.00097 | $0.01728 |
| Opus 5 | $0.00048 | $0.00864 |
| Sonnet 5 | $0.00019 | $0.00346 |
| Haiku 4.5 | $0.00010 | $0.00173 |
Grade A, and why
review-user-prompt-english 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 12d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
English Language Reviewer
Scan every user message for grammar, spelling, punctuation, articles, prepositions, tense, subject-verb agreement, word choice, and awkward phrasing. Threshold: flag what would be wrong in a semi-formal email to a colleague; ignore chat-speak (no greeting, intentional fragments, lowercase start).
The reviewer MUST be invisible on a clean pass. When the message has no mistakes, output nothing about the review — no block, no "looks good", no acknowledgement.
Prioritize structural errors that non-native speakers often miss because the sentence is still understandable — these are the highest-value corrections:
- Tense with since/for: "I'm working here since Monday" → "I've been working here since Monday"
- Embedded question order: "I don't know what is the problem" → "I don't know what the problem is"
- Article omission: "return correct response" → "return the correct response"
- Uncountable nouns: "informations", "advices", "equipments"
- Prepositions: "depend of" → "depend on", "interested for" → "interested in"
List every mistake — never truncate or summarize. But if the same rule is broken many times, they all go under one header as stacked diffs; do not repeat the rule as separate groups.
The review is rule-centric, not phrase-centric. Group every correction by the underlying rule.
When there are no mistakes
Output nothing. No block, no header, no "No mistakes", no "looks good", no "everything reads cleanly", no summary of why the message was clean, no acknowledgement of any kind. The review is invisible on a clean pass — proceed directly to the main response as if the reviewer had never run.
Never emit anything like this:
───────── English review ─────────
No mistakes — "A new day dawned" is a nicely stylized opener and everything else reads cleanly.
──────────────────────────────────
Not an empty block. Not a single-line "no mistakes found" note. Not a compliment on the phrasing. If there are zero corrections to make, the review produces zero output. Silence is the correct behavior.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 177 lines · 97 tokens per session scan A b52f637443e0
review-user-prompt-english is a skill published in the GitHub repository swapii/claude-linguist (3 stars, last pushed 4mo ago), licensed MIT. It adds 97 tokens to every session and 1,728 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 2026-08-31.
Other skills, from other repositories
github-pr-review
Handles PR review comments and feedback resolution. Use when user wants to resolve PR comments, handle review feedback, fix review comments, address PR review, check review status, respond to reviewer, verify PR readiness, review PR comments, analyze review feedback, evaluate PR comments, assess review suggestions, or…
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
anthropic-validator
Validates Claude Code assets (skills, hooks, agents, commands, MCP servers, plugins) against official Anthropic standards. Fetches latest docs dynamically and produces structured validation reports.
continuous-feedback
Identifies improvement targets from accumulated session learnings and proposes concrete skill/agent modifications. General-purpose pipeline for any Claude Code project.
create-subagent
Generates single-purpose Claude Code sub-agents for use via the Task tool. Use when creating dedicated sub-agents, scaffolding agent definitions, or generating agents with diagnostics and permissions setup.
bug-magnet-data
Curated edge case test data for boundary testing, verification scripts, and test generation. Provides pre-curated reference data organized by data type with context-specific loading guidance.