cuecards AGENTS.md

Install

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.

agentmods

npx agentmods add instructions/opencue/cuecards/agents-md

Clone the repo

git clone --depth 1 https://github.com/opencue/cuecards

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/opencue/cuecards/agents-md.svg)](https://agentmods.dev/instructions/opencue/cuecards/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/opencue/cuecards/agents-md"><img src="https://agentmods.dev/badge/instructions/opencue/cuecards/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,440 This file is loaded in full into every session.

When invoked 1,440 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin unknown No closer match found in the catalogue.

Token cost

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	$0.01440	$0.01440
Opus 5	$0.00720	$0.00720
Sonnet 5	$0.00288	$0.00288
Haiku 4.5	$0.00144	$0.00144

Measured today against content hash ff9ecc35fe7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 today.

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.

AGENTS.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 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 ruler distributes a profile's rules[] into every agent's native rule file (CLAUDE.md, AGENTS.md, .cursorrules, …). Set CUE_RULER_AUTO=1 to sync them on every cue 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 -s for Linux/macOS and $OS / $env:OS for 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.md inside WSL
- parallel agents: setup/parallel-agents.md, only after lean stack works
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 core unless 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, narrow rg, sed -n, head, or tail before 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; run cue validate --all only 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.ts and profile resolution tests under src/lib/cwd-resolver.test.ts.

Read the full file on GitHub · 101 lines

Changes

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.

today First seen · 101 lines · 1,440 tokens per session scan A ff9ecc35fe7d

Subscribe to this mod's changes

cuecards AGENTS.md is an instructions file published in the GitHub repository opencue/cuecards (5 stars, last pushed yesterday), licensed MIT. It adds 1,440 tokens to every session, about $0.0072 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 2026-09-03.

agent-framework agent-skill ai-agents ai-coding anthropic claude

paad CLAUDE.md

Claude Code instructions for Ovid/paad, covering claude.md — paad, what this project is, project structure, the two trees and which checks run per tree.

Ovid/paad · 5,565 tokens

semantix CLAUDE.md

Claude Code instructions for Gnosil/semantix, covering 项目规则（claude code）, 1. 改动须经用户过目；由 claude 提交到分支 + pr，用户 review 后合并 and 2. 本地实验区：论文数据与实验材料不进 github.

Gnosil/semantix · 561 tokens

BuildersGate CLAUDE.md

Claude Code instructions for Thepizzapie/BuildersGate, covering setting up builders gate for a user, ask two things first, install, point it at a game and keys.

Thepizzapie/BuildersGate · 1,915 tokens

stagecraft AGENTS.md

AGENTS.md instructions for telus-labs/stagecraft, covering agents.md, start here (in order), test and lint commands, where things live and load-bearing contracts (do not break without an adr).

telus-labs/stagecraft · 1,093 tokens

awesome-agent-infrastructure CLAUDE.md

Instructions for backblaze-labs/awesome-agent-infrastructure, covering claude.md — awesome-agent-infrastructure, what this list is, scope and files, schema, workflow, rules.

backblaze-labs/awesome-agent-infrastructure · 370 tokens

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).

microsoft/vscode · 6,785 tokens