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 sorah/config --skill english-textgit clone --depth 1 https://github.com/sorah/configWrote 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/sorah/config/english-text)<a href="https://agentmods.dev/skills/sorah/config/english-text"><img src="https://agentmods.dev/badge/skills/sorah/config/english-text/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/sorah/config/english-text"><img src="https://agentmods.dev/badge/skills/sorah/config/english-text.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 | $0.00105 | $0.02800 |
| Opus 5.5 | $0.00042 | $0.01120 |
| Sonnet 5.5 | $0.00021 | $0.00560 |
| Haiku 4.5 | $0.00011 | $0.00280 |
Grade A, and why
english-text 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 yesterday.
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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
English Text
Conventions for writing English in the author's voice. Derived from the author's GitHub comments and PR bodies (2018–2025), git commit messages (2012–2026), and English business emails from the RubyKaigi sponsorship desk (2018–2026). Context-specific conventions always take priority.
The author is a non-native English writer whose voice is terse, direct, and technical. Reproduce the voice, not the mistakes: write grammatical English with the same rhythm and economy.
Related skills:
- Commit subject lines and prefixes: /sorah-guides:commit-style
- RubyKaigi sponsor broadcasts, portal text, terminology: rubykaigi-english-writing and rubykaigi-glossary (rubykaigi-comms plugin). This skill covers the general voice underneath them.
Writing Contexts & Register
Identify the context before writing. Register scales with audience distance:
- Own or team repositories (PR bodies, issues, review comments): terse fragments, lowercase sentence start allowed, link-first, trailer-style references. A body may be a single line or a bare URL.
- Upstream / third-party projects (issues, PRs to projects the author doesn't maintain): capitalised full sentences, problem first then reason, cite specs/RFCs/upstream issues.
## Description/## Verificationheadings only for long PRs, or fill the project's issue template. - Maintainer replies on own projects (to users and contributors): short and decisive. Decline plainly with a reason and state what would be accepted.
- Code review: often just a
```suggestionblock, or a one-line question or claim with a hedge on technical correctness. - Commit bodies: usually absent. When present, one clause continuing the subject, or a short cause → effect explanation. See "Commit Bodies" below.
- Business email (sponsors, vendors, partners): answer-first, short paragraphs, firm on policy, warm in small doses. See
references/email.md.
When the language choice is ambiguous (e.g. a Japanese-community repo), check surrounding comments; Japanese-community reviews are often written in Japanese even when the PR body is English.
What ships with it
2 files 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.
- yesterday First seen · 140 lines · 105 tokens per session scan A ebde5114c2ce
english-text is a skill published in the GitHub repository sorah/config (31 stars, last pushed yesterday), licensed MIT. It adds 105 tokens to every session and 2,800 once invoked, about $0.0004 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 2026-10-17.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.