writing-voice

Writing rules for user-facing text produced by webhook.co, including documentation, interface text, command-line output, errors, changelogs, and README files. They define a clear, concise, developer-to-developer tone.

In plain words
What is it for?
Use them when writing or editing any prose that users or developers will read in webhook.co.
Why use it?
They keep wording consistent across the product and reduce jargon, hype, and unclear instructions.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/webhook-co/webhook/writing-voice
Clone the repo
git clone --depth 1 https://github.com/webhook-co/webhook

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 305 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00305
Opus 5 $0.00000 $0.00152
Sonnet 5 $0.00000 $0.00061
Haiku 4.5 $0.00000 $0.00030

Measured yesterday against content hash 4563b6404e5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

writing-voice 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.

.cursor/rules/writing-voice.mdc · 24 lines

What it actually says

Writing voice

Apply to anything a user reads: docs, dashboard copy, CLI output, error messages, changelogs.

  • Precise & quietly opinionated. Have a point of view and state it plainly; recommend the right path instead of listing every option. Sage + Creator, not hype.
  • Casual-professional, developer-to-developer. Write like a sharp colleague. Contractions are fine. Cut needless jargon; when a term is necessary, define it once.
  • Dry, sparing wit — never at the expense of clarity. If a joke risks confusing the reader, drop the joke.
  • Lowercase brand names: webhook.co and wbhk.my, even at the start of a sentence where it reads naturally.
  • Sentence case for headings, titles, buttons, and UI labels.
  • Tie-breakers: when wording choices conflict, optimize for clarity first, then trust. Be honest about limits and tradeoffs; never overpromise.
  • Prefer active voice, short sentences, and concrete examples over abstraction. Lead with what the reader can do.
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.

  1. yesterday First seen · 24 lines · 305 tokens per session scan A 4563b6404e5a

Subscribe to this mod's changes

writing-voice is a cursor rule published in the GitHub repository webhook-co/webhook (0 stars, last pushed 6d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 305 tokens. 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.