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 agentmods add instructions/exmergo/skill-no-em-dashes/agents-mdgit clone --depth 1 https://github.com/exmergo/skill-no-em-dashesWrote 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/instructions/exmergo/skill-no-em-dashes/agents-md)<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>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 | $0.00744 | $0.00744 |
| Opus 5 | $0.00372 | $0.00372 |
| Sonnet 5 | $0.00149 | $0.00149 |
| Haiku 4.5 | $0.00074 | $0.00074 |
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.
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
- Never use an em dash (the character U+2014) as punctuation.
- 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--wordor a spaced--), a hyphen padded with spaces (-), a stray en dash (U+2013) between words, and the horizontal bar (U+2015). - 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.
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.
- 6d ago First seen · 63 lines · 744 tokens per session scan A 340bad076767
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.
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.
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).
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.
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.
SeekMoney-ai CLAUDE.md
Claude Code instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.
obsidian-ai CLAUDE.md
Instructions for spencermarx/obsidian-ai, covering claude.md, project overview, build & development commands, architecture and key design decisions.