Emdash is a desktop environment for running multiple AI coding agents in parallel, isolating each task in its own Git worktree. Developers use it to send work from issue trackers to coding agents, review changes, inspect checks, and merge results across local projects or remote machines.
Borrowing it
Nothing to install: this file belongs to generalaction/emdash. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/generalaction/emdash/main/AGENTS.mdgit clone --depth 1 https://github.com/generalaction/emdashWrote 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/generalaction/emdash/agents-md)<a href="https://agentmods.dev/instructions/generalaction/emdash/agents-md"><img src="https://agentmods.dev/badge/instructions/generalaction/emdash/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/generalaction/emdash/agents-md"><img src="https://agentmods.dev/badge/instructions/generalaction/emdash/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.05657 | $0.05657 |
| Opus 5.5 | $0.02263 | $0.02263 |
| Sonnet 5.5 | $0.01131 | $0.01131 |
| Haiku 4.5 | $0.00566 | $0.00566 |
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 15d 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 — 420 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Overview
Emdash is a local-first, cross-platform Electron app for running multiple AI coding agents in parallel. Each task is isolated in its own Git worktree and can run locally or over SSH, while the desktop app coordinates provider CLIs, ACP chat sessions, terminal sessions, issue and PR integrations, diff review, and release packaging.
Repository Structure
This is a pnpm workspace monorepo. The Electron app lives in
apps/emdash-desktop/ as @emdash/emdash-desktop; shared packages live under
packages/. Unless a path is prefixed with packages/ or another app, app paths
such as src/..., drizzle/, scripts/, and build/ are relative to
apps/emdash-desktop/.
Repo root:
.claude/- Local Claude agent settings for this checkout..github/- GitHub issue templates, reusable actions, CI, and release workflows.agents/- Agent-facing architecture, workflow, convention, integration, and risk docs.apps/emdash-desktop/- The Electron desktop app.apps/workspace-server/- Remote workspace server and its Docker-based dev stack.packages/chat-ui/- Shared transcript and ACP chat renderer with Storybook coverage.packages/core/- Transport-agnostic runtime primitives, including ACP session logic.packages/plugins/- Agent provider plugin definitions, hooks, and ACP adapters.packages/shared/- Shared primitives such as result types, logging, and markdown helpers.packages/theme/- Theme token codegen that emits the generated theme CSS.packages/ui/- Shared React UI components, theme tokens, recipes, and primitives.packages/wire/- Typed wire protocol contracts shared by app and workspace server.pnpm-workspace.yaml- Workspace package globs forapps/*andpackages/**.- Root config files -
package.json,nx.json,.nvmrc,.oxfmtrc.json,.oxlintrc.json, and lockfile/configuration owned at the workspace root.
Inside apps/emdash-desktop/:
build/- Electron packaging assets; avoid edits unless working on packaging/signing.drizzle/- Generated Drizzle SQL migrations and metadata.scripts/- Release, verification, and build support scripts.src/main/- Electron main process: bootstrap, Wire gateway, DB, and host services.src/entry/- Electron entry points:main.ts(main process) andpreload.ts, the typed preload bridge exposed to the renderer.src/renderer/- React composition shell, shared browser infrastructure, and tests.src/core/- Vertical slices with portable APIs, Node implementations, browser UI, and manifests.src/types/- Ambient and cross-cutting TypeScript declarations.tooling/- App-level development and test infrastructure not bundled into production.
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.
- 15d ago Changed · +14 tokens per session 3575591c322e
- 2mo ago First seen · 420 lines · 5,643 tokens per session scan A 75df1adfbc3c
emdash AGENTS.md is an instructions file published in the GitHub repository generalaction/emdash (6,198 stars, last pushed 4d ago), licensed Apache-2.0. It adds 5,657 tokens to every session, about $0.0226 per session on Opus 5.5. 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.
emdash AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| emdash AGENTS.mdgeneralaction/emdash | Instructions file | 6.2k | 4d ago | Apache-2.0 | A | 5,657 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |