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/emdash-cms/emdash/agents-mdgit clone --depth 1 https://github.com/emdash-cms/emdashWhat 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 | $0.06366 | $0.06366 |
| Opus 5 | $0.03183 | $0.03183 |
| Sonnet 5 | $0.01273 | $0.01273 |
| Haiku 4.5 | $0.00637 | $0.00637 |
Grade A, and why
emdash 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 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 — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This file provides guidance to agentic coding tools working in this repository.
For human-facing contributor info (setup, repo layout, PR policy, i18n), see CONTRIBUTING.md. This file focuses on the patterns and gotchas an agent needs to write correct code.
CLAUDE.md is a symlink to this file. .agents/skills and .claude/skills are symlinks to skills/. Don't try to sync between them.
When writing, revising, or reviewing documentation, load the writing-emdash-docs skill. Use it for public docs, READMEs, contributor guidance, technical specifications, release notes and changesets, and skill instructions.
Rules
Backwards compatibility matters. EmDash is published and in active use, pre-1.0. Prefer additive changes (new fields, new routes, new options with defaults). Breaking changes need an explicit decision, a package bump, and a changeset that calls the break out clearly. Database migrations are forward-only -- never write one that leaves existing content inaccessible. When in doubt, open a Discussion.
TDD for bugs. Failing test -> fix -> verify. A bug without a reproducing test is not fixed.
Localize everything user-facing. All admin UI strings, aria labels, and toast messages go through Lingui. All admin layout uses RTL-safe logical Tailwind classes. See Localization and RTL.
Scope discipline. No drive-by refactors, no bulk lint/type cleanups, no "while I'm here" edits in unrelated files. If you see a systemic issue, open a Discussion. See CONTRIBUTING.md § Contribution Policy.
Never add queries to the logged-out hot path. Any change that increases the query count of a logged-out route needs a really good reason -- and that includes cold-start or first-request-only queries, not just steady state. See Performance.
Comments are for code readers, not reviewers. Write a comment only when the code can't be made clearer, or to give a non-obvious "why". Never justification, narrative, or issue/PR references. See Comments.
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 · 413 lines · 6,366 tokens per session scan A 353f62341445
emdash AGENTS.md is an instructions file published in the GitHub repository emdash-cms/emdash (12,111 stars, last pushed 3d ago), licensed MIT. It adds 6,366 tokens to every session, about $0.0318 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 2026-08-30.
Other instructions, from other repositories
emdash-claude-plugin CLAUDE.md
Claude Code instructions for EngDawood/emdash-claude-plugin, covering plugin structure, skills, agents, documentation and rules.
intlayer CLAUDE.md
Instructions for aymericzip/intlayer, covering repo layout, commands (run from root), content declaration flow, git and commit conventions.
stardrive AGENTS.md
Instructions for peltmonger/stardrive, covering 🛑 critical: repository bootstrap directive 🛑, general information and guidelines for ai agents, analyze your high-level use case first, how the .ai guidance files relate and this is an astro project.
webiny-js AGENTS.md
AGENTS.md instructions for webiny/webiny-js, covering exploration, persist learnings, code, building and testing.
webiny-js CLAUDE.md
Claude Code instructions for webiny/webiny-js, covering context, claude project guidelines, reading code, development commands and install dependencies (suppress all output – it's noise).
stardrive copilot-instructions.md
Instructions for peltmonger/stardrive: Follow AGENTS.md for repository mode selection, project conventions, and applicable workflow guides.