docs-plain-language

docs-plain-language is a cursor rule for Cursor from alexeyleshchenko/fast-mcp-telegram. It costs 0 tokens per session (536 once invoked), scanned A, a copy of docs-plain-language, MIT.

A set of writing rules for producing clear documentation without unnecessary technical slang.

In plain words
What is it for?
Use it when writing or editing READMEs, documentation, security files, contribution guides, architecture records, or project memory notes.
Why use it?
It helps new operators and contributors understand instructions and results without decoding project-specific terms.

Cursor rule for Cursor

Written for Cursor: installed under .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/alexeyleshchenko/fast-mcp-telegram/docs-plain-language
Clone the repo
git clone --depth 1 https://github.com/alexeyleshchenko/fast-mcp-telegram

Made for: Cursor.

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.

agentmods badge for docs-plain-language

README.md
[![agentmods](https://agentmods.dev/badge/rules/alexeyleshchenko/fast-mcp-telegram/docs-plain-language.svg)](https://agentmods.dev/rules/alexeyleshchenko/fast-mcp-telegram/docs-plain-language)
Your own site
<a href="https://agentmods.dev/rules/alexeyleshchenko/fast-mcp-telegram/docs-plain-language"><img src="https://agentmods.dev/badge/rules/alexeyleshchenko/fast-mcp-telegram/docs-plain-language.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 536 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 5.1 $0.00000 $0.00536
Opus 5 $0.00000 $0.00268
Sonnet 5 $0.00000 $0.00107
Haiku 4.5 $0.00000 $0.00054

Measured 5d ago against content hash d3b06d733f09, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

docs-plain-language 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 5d 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.

Origin

This is a copy

100% identical to docs-plain-language — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.cursor/rules/docs-plain-language.mdc · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plain-language documentation

When editing Markdown (README, docs/, SECURITY.md, CONTRIBUTING.md, ADRs, memory bank, example YAML comments):

Goal

A new operator or contributor should understand what to do and what happens without decoding project slang.

Keep (widely used or project-defined once)

  • Standard product terms after a short gloss: MCP, Bearer token, principal, principal identifier, http-auth, Telegram, MTProto, ACL
  • Env vars and YAML keys as literals: ACL_ENABLED, allow_mtproto, chats
  • Linked internal names when they are the actual config surface (file paths, tool names)

Avoid or replace

Avoid Prefer
Invented shorthand (bot-like, power profile without table context) Names from SECURITY.md / examples: bot, team_lane, analyst
Phase/version jargon alone (“Phase 2 guardrails”) What changed: “listed principals need allow_mtproto: true for raw MTProto”
Implementation slang without explanation (“synthetic rule”, “empty lane”) Plain outcome: “principal not in principals: is denied” or “listed principal with no chats cannot use chat tools”
-like, -style, “footgun”, “blast radius” in operator runbooks Direct risk: “teammates with the same principal identifier can read login codes”
Stacking nouns (“dual pre/post enforcement”) One sentence: what is checked before the tool runs and what is filtered after

Style

  • Prefer tables for profiles and flags; one row = one audience action.
  • First mention of a restriction: symptom → cause → fix (troubleshooting), not error-code archaeology.
  • Example tokens in tests/docs: use names from acl.yaml.example (automation-token), not cute internal labels.
  • English only; short sentences; active voice (“Set allow_mtproto: true”) over passive stacks.

Quick check before finishing doc edits

  1. Would someone who only runs http-auth understand this without reading session_acl.py?
  2. Did every coined phrase appear in a glossary table or get removed?
  3. Are env vars and YAML keys copy-pasteable and spelled exactly as in code?

Read the full file on GitHub · 43 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.

  1. 5d ago First seen · 43 lines · 0 tokens per session scan A d3b06d733f09

Subscribe to this mod's changes

docs-plain-language is a cursor rule published in the GitHub repository alexeyleshchenko/fast-mcp-telegram (2 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 536 tokens. A static security scan graded it A with 0 findings. It is 100% identical to docs-plain-language, differing in 0 lines, and is treated as a copy.