skill-no-em-dashes AGENTS.md

skill-no-em-dashes AGENTS.md is an instructions file for Codex, OpenCode from exmergo/skill-no-em-dashes. It costs 744 tokens per session, scanned A, original, MIT.

A repository-wide writing policy that bans em dashes and look-alike punctuation used in their place.

In plain words
What is it for?
Use it when writing or editing project text, especially when applying the rules from the repository's AGENTS.md file.
Why use it?
It makes prose follow a deliberate punctuation style across documentation, code comments, commits, emails, and other text.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

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 instructions/exmergo/skill-no-em-dashes/agents-md
Clone the repo
git clone --depth 1 https://github.com/exmergo/skill-no-em-dashes

Made for: Codex, OpenCode.

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 skill-no-em-dashes AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/exmergo/skill-no-em-dashes/agents-md.svg)](https://agentmods.dev/instructions/exmergo/skill-no-em-dashes/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/exmergo/skill-no-em-dashes/agents-md"><img src="https://agentmods.dev/badge/instructions/exmergo/skill-no-em-dashes/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 744 This file is loaded in full into every session.
When invoked 744 The same file — it is already loaded in full.
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 5.1 $0.00744 $0.00744
Opus 5 $0.00372 $0.00372
Sonnet 5 $0.00149 $0.00149
Haiku 4.5 $0.00074 $0.00074

Measured 6d ago against content hash 340bad076767, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

skill-no-em-dashes AGENTS.md 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 6d 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.

AGENTS.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing style: no em dashes

These rules apply to any prose you write or edit: drafts, documentation, commit messages, pull request descriptions, comments, emails, marketing copy, and essays. The goal is writing that contains no em dashes and is built from sentences that never reach for one in the first place.

Why it matters: heavy em-dash use is one of the most recognizable fingerprints of machine-written text, and removing it forces tighter, more deliberate sentences.

The rule

  1. Never use an em dash (the character U+2014) as punctuation.
  2. Do not smuggle the same pause back in with a look-alike. These are banned when they do an em dash's job: a double hyphen (word--word or a spaced --), a hyphen padded with spaces (-), a stray en dash (U+2013) between words, and the horizontal bar (U+2015).
  3. Replace the construction with real punctuation, roughly in this order: comma, semicolon, colon, period, parentheses. When a plain swap reads awkwardly, recast the sentence rather than forcing a substitute.

Match the replacement to the job

An em dash is almost always doing one of a few jobs. Identify it, then replace it. In the examples below, [em dash] marks where the original reached for one.

  • Dramatic reveal ("She wanted one thing [em dash] to win"): use a colon, or split into two sentences.
  • "Not X but Y" pivot ("This isn't a tool [em dash] it's a platform"): recast as "This is a platform, not just a tool", or use a semicolon.
  • Interruptive aside ("The plan [em dash] which nobody liked [em dash] was scrapped"): use commas for a mild aside, parentheses for a true one.
  • Two joined clauses ("It compiles [em dash] and it's fast"): use a semicolon, a comma plus conjunction, or two sentences.
  • Summary dash ("Speed, clarity, polish [em dash] that's the goal"): recast around a colon, or split into sentences.
  • Interrupted dialogue: use a hard stop carried by narration, or an ellipsis for a line that trails off. This is the one job with no clean comma or semicolon swap.

Read the full file on GitHub · 63 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. 6d ago First seen · 63 lines · 744 tokens per session scan A 340bad076767

Subscribe to this mod's changes

skill-no-em-dashes AGENTS.md is an instructions file published in the GitHub repository exmergo/skill-no-em-dashes (8 stars, last pushed 2mo ago), licensed MIT. It adds 744 tokens to every session, about $0.0037 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.

Related

Other instructions, from other repositories

multai CLAUDE.md

Claude Code instructions for alo-exp/multai, covering multai — claude code instructions, 0. session startup (automatic), project overview, 1. automated enforcement and 2. active workflow.

alo-exp/multai · 1,904 tokens

Skill_Seekers CLAUDE.md

Instructions for yusufkaraaslan/Skill_Seekers, covering claude.md, project overview, essential commands, required before running tests or cli (src/ layout) and run all tests (never skip - all must pass before commits).

yusufkaraaslan/Skill_Seekers · 5,387 tokens

platform-skills copilot-instructions.md

Copilot instructions for nitinjain999/platform-skills, covering platform engineering instructions for github copilot, version: 1.40.0, source: https://github.com/nitinjain999/platform-skills, response contract and core principles.

nitinjain999/platform-skills · 3,564 tokens

claude-code-toolkit CLAUDE.md

Claude Code instructions for robertguss/claude-code-toolkit, covering claude.md, project overview, build commands, package a single skill for claude.ai upload and package all skills.

robertguss/claude-code-toolkit · 617 tokens

SeekMoney-ai CLAUDE.md

Claude Code instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.

zykooooooooo/SeekMoney-ai · 2,178 tokens

obsidian-ai CLAUDE.md

Instructions for spencermarx/obsidian-ai, covering claude.md, project overview, build & development commands, architecture and key design decisions.

spencermarx/obsidian-ai · 1,165 tokens