Borrowing it
Nothing to install: this file belongs to opencue/cuecards. 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/opencue/cuecards/main/AGENTS.mdgit clone --depth 1 https://github.com/opencue/cuecardsWrote 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/opencue/cuecards/agents-md)<a href="https://agentmods.dev/instructions/opencue/cuecards/agents-md"><img src="https://agentmods.dev/badge/instructions/opencue/cuecards/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/opencue/cuecards/agents-md"><img src="https://agentmods.dev/badge/instructions/opencue/cuecards/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 | $0.01666 | $0.01666 |
| Opus 5.5 | $0.00666 | $0.00666 |
| Sonnet 5.5 | $0.00333 | $0.00333 |
| Haiku 4.5 | $0.00167 | $0.00167 |
Grade A, and why
cuecards 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 1mo 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS - cue bootstrap contract
Keep this file lean. It is read by coding agents that help install or maintain
cue. Detailed context-budget and install notes live in
docs/agent-context-budget.md; open that doc only when the task needs it.
What cue is
cue is an agent profile manager for Claude Code and Codex. It sits between the
user's shell and the real claude / codex binary, resolves the active profile
from cwd, materializes a per-profile runtime under ~/.config/cue/runtime/, and
then execs the real agent.
Key paths:
profiles/- bundled profile definitions.resources/skills/- installable skills.resources/mcps/- MCP server configs.resources/rules/- shared rule library;cue rulerdistributes a profile'srules[]into every agent's native rule file (CLAUDE.md, AGENTS.md, .cursorrules, …). SetCUE_RULER_AUTO=1to sync them on everycue launch(safe mode: never overwrites a hand-written file).setup/- per-OS install prompts.docs/launch.md- resolve -> materialize -> exec flow.
Bootstrap Rules
- Detect the OS before shell work:
uname -sfor Linux/macOS and$OS/$env:OSfor Windows. - Pick one setup file and load only that file:
- lean stack:
setup/lean-cue.md - macOS:
setup/macos.md - Linux:
setup/linux.md - Windows:
setup/windows.md - WSL2: use
setup/linux.mdinside WSL - parallel agents:
setup/parallel-agents.md, only after lean stack works
- lean stack:
- Ask before hard-to-reverse or external steps: shell profile edits, existing
Claude/Codex config merges, global package installs,
sudo, or downloads. - Run one setup phase at a time and verify after each phase.
- Keep installs idempotent. Guard each install with an existence check.
- Do not auto-enable plugins until the user confirms the exact settings write.
- Default profile should stay
coreunless the user explicitly chooses a broader composite.
Repo Work Rules
- Preserve user work. Do not revert, reset, or overwrite unrelated changes.
- Prefer small, source-backed changes over broad rewrites.
- For repo architecture, feature-flow, or symbol-impact questions, use CodeGraph before broad file reads or grep.
- For context-heavy files, inspect with
wc, narrowrg,sed -n,head, ortailbefore reading more. - Do not paste large fixtures, catalogs, generated files, full logs, or full setup manuals into chat.
- Verify with the smallest check that proves the touched surface. For profile
edits, start with
cue validate <profile>plus targeted tests; runcue validate --allonly when requested or when a shared loader/materializer change creates real cross-profile risk. - For default-profile behavior, source of truth is
src/commands/init.tsand profile resolution tests undersrc/lib/cwd-resolver.test.ts.
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.
- 1mo ago Changed · +16 lines · +226 tokens per session 1d51a681110a
- 1mo ago First seen · 101 lines · 1,440 tokens per session scan A ff9ecc35fe7d
cuecards AGENTS.md is an instructions file published in the GitHub repository opencue/cuecards (6 stars, last pushed yesterday), licensed MIT. It adds 1,666 tokens to every session, about $0.0067 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 2026-09-03.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.