Borrowing it
Nothing to install: this file belongs to ensemblr-hq/ensemblr. 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/ensemblr-hq/ensemblr/master/AGENTS.mdgit clone --depth 1 https://github.com/ensemblr-hq/ensemblrWrote 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/ensemblr-hq/ensemblr/agents-md)<a href="https://agentmods.dev/instructions/ensemblr-hq/ensemblr/agents-md"><img src="https://agentmods.dev/badge/instructions/ensemblr-hq/ensemblr/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/ensemblr-hq/ensemblr/agents-md"><img src="https://agentmods.dev/badge/instructions/ensemblr-hq/ensemblr/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 | $0.03214 | $0.03214 |
| Opus 5.5 | $0.01286 | $0.01286 |
| Sonnet 5.5 | $0.00643 | $0.00643 |
| Haiku 4.5 | $0.00321 | $0.00321 |
Grade A, and why
ensemblr 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 25d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
These instructions apply to the whole repository.
Repository Layout
This is a Bun workspaces monorepo.
| Path | What lives there |
|---|---|
apps/desktop/ |
Ensemblr, the Electron desktop app: its source, tests, scripts, docs, JSON Schemas, assets, Nix packaging, changelog, and release notes. |
apps/website/ |
The marketing and documentation site. Not started yet. |
packages/shared/ |
Code the apps share, such as UI pieces lifted out of the desktop app. Not started yet. |
The root holds only what the whole repository shares: the workspace manifest (package.json) and lockfile, the install settings (bunfig.toml; the toolchain itself is the Nix dev shell in flake.nix), the house Biome config, the monorepo-level scripts in scripts/, CI (.github/), agent tooling (.claude/, .codex/, .agents/, .mcp.json), Ensemblr's repository settings (.ensemblr/), the Nix flake entrypoint, and the community files. Keep it that way: anything that belongs to one app or package lives under that workspace's directory.
- Before working under
apps/desktop/, readapps/desktop/AGENTS.md. Its paths, and those in the scopedAGENTS.mdfiles beneath it, are relative toapps/desktop/. - When you write a path in prose, write it from the repository root, workspace prefix included —
apps/desktop/src/main/main.ts, notsrc/main/main.ts.
Workspaces
- The root
package.jsonworkspacesglobsapps/*andpackages/*; a directory becomes a workspace when it gets apackage.json. Name a new package@ensemblr/<name>, mark itprivate, and depend on another workspace with"workspace:*". The desktop app keeps the package nameensemblr, which its Electron identity and release tooling read. - Bun runs a workspace's own
preinstallandpostinstallonly when it first installs that workspace — not when a dependency changes, and not on an install with nothing to do. The root manifest'spreinstallandpostinstalltherefore run every workspace's (bun run --workspaces --if-present) on every install, the way a single-package root's ran before; on a first install they run twice, so keep them idempotent. - Each workspace owns its
check,typecheck, andtestscripts. The root's scripts of the same name run every workspace's (bun run --workspaces --if-present <script>);checkfirst runs the lockfile check and Biome over the whole tree (each file under its nearestbiome.json). - Install from anywhere with
bun installorbun ci; Bun installs every workspace and hoists dependencies into the rootnode_modules. Add a dependency to the workspace that uses it (bun add <pkg>inside that workspace's directory, orbun add <pkg> --cwd apps/desktop), never to the root manifest. - A new workspace manifest changes what
bun installlays out, so it moves the Nix deps hash: re-pin withapps/desktop/nix/update-pins.sh deps(thenix-depscheck reports the new hash on a pull request).
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.
- 25d ago Changed · +2 lines · +118 tokens per session 5fa8d813868c
- 26d ago Changed · -39 lines · -1,684 tokens per session 66119cdc314f
- 28d ago Changed · +71 tokens per session c25aa16594cc
- 1mo ago Changed · +5 lines · +538 tokens per session bc119efc71be
- 1mo ago Changed · +40 tokens per session 94a6be94afe1
- 1mo ago First seen · 158 lines · 4,131 tokens per session scan A 11cf4292bb56
ensemblr AGENTS.md is an instructions file published in the GitHub repository ensemblr-hq/ensemblr (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,214 tokens to every session, about $0.0129 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.