Borrowing it
Nothing to install: this file belongs to cardstack/boxel. 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/cardstack/boxel/main/AGENTS.mdgit clone --depth 1 https://github.com/cardstack/boxelWrote 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/cardstack/boxel/agents-md)<a href="https://agentmods.dev/instructions/cardstack/boxel/agents-md"><img src="https://agentmods.dev/badge/instructions/cardstack/boxel/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/cardstack/boxel/agents-md"><img src="https://agentmods.dev/badge/instructions/cardstack/boxel/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 | $0.07487 | $0.07487 |
| Opus 5.5 | $0.02995 | $0.02995 |
| Sonnet 5.5 | $0.01497 | $0.01497 |
| Haiku 4.5 | $0.00749 | $0.00749 |
Grade A, and why
boxel 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 — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions for AI Agents
Type checking
- Use
glint(notglint --declaration) for type checking. The--declarationflag emits hundreds of.d.tsfiles that pollute the working tree. - Never use
tscdirectly — this project uses glint for type checking.
Tooling prerequisites
- We pin the toolchain with mise (
.mise.toml), which manages Node.js and pnpm versions. Runmise installfrom the repo root to get the correct versions—avoid global installs outside mise. - pnpm is required for all scripts; use the pinned version as specified above.
- Docker is required (Postgres, Synapse, SMTP, Stripe CLI container). Ensure the daemon is running and you can run
dockerwithout sudo.
Parallel agent sessions
- Other sessions may be live on this machine, and — when Remote Control is enabled — on the user's other machines and in the cloud.
ListAgentsnames them, labelled by kind, andSendMessageaddresses one by name. Coordinate rather than duplicating work; theagent-peer-collaborationskill carries the protocol and the shared-resource rules. - Enabling cross-machine reachability is a human step, documented in docs/parallel-claude-sessions.md. If a peer you expect is missing from
ListAgents, say so instead of assuming it is gone — a session without Remote Control is simply invisible there.
GitHub Actions failure triage helper
- Use
pnpm ci:failures -- ...to quickly summarize failed jobs and extract actionable test failures from GitHub Actions logs. - This command requires GitHub CLI (
gh) to be installed and authenticated. - Common usage:
pnpm ci:failures -- --run <run-id-or-url>pnpm ci:failures -- --pr <pr-number-or-url>pnpm ci:failures -- --branch <branch-name>
- Useful flags:
--repo <owner/repo>to target a specific repository--workflow <name>to focus on a specific workflow (for exampleCI Host)--max-lines <n>to limit extracted failure lines--context-lines <n>to include surrounding stack/assertion context for each failure--no-progressto suppress progress updates if you only want final output--jsonfor machine-readable output--fail-on-findingsto exit non-zero when failed jobs are found
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 Changed · +3 lines · +112 tokens per session d9d38bf1e361
- 5d ago First seen · 393 lines · 7,375 tokens per session scan A 1d0e24d485b8
boxel AGENTS.md is an instructions file published in the GitHub repository cardstack/boxel (27 stars, last pushed today), licensed MIT. It adds 7,487 tokens to every session, about $0.0299 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 2026-10-21.
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.