cuecards: Command for Claude Code

.claude/commands/generate-llms.md

generate-llms is a command for Claude Code from opencue/cuecards. It costs 33 tokens per session (565 once invoked), scanned A, original, MIT.

A command that regenerates the product's llms.txt files from its README, technical documentation, profiles, and package information. These files give AI tools a compact description of a project.

In plain words
What is it for?
Use it after updating the README, profiles, or agent support to refresh both llms.txt copies.
Why use it?
It keeps the project's AI-discovery files aligned with current documentation and supported agents after significant changes.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

This is opencue/cuecards's own configuration. It tells Claude Code how to work on cuecards itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cuecards configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/opencue/cuecards/main/.claude/commands/generate-llms.md
Clone the repo
git clone --depth 1 https://github.com/opencue/cuecards

Made for: Claude Code.

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.

agentmods badge for generate-llms

README.md
[![agentmods](https://agentmods.dev/badge/commands/opencue/cuecards/generate-llms.svg)](https://agentmods.dev/commands/opencue/cuecards/generate-llms)
Your own site
<a href="https://agentmods.dev/commands/opencue/cuecards/generate-llms"><img src="https://agentmods.dev/badge/commands/opencue/cuecards/generate-llms.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 565 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.00565
Opus 5 $0.00016 $0.00282
Sonnet 5 $0.00007 $0.00113
Haiku 4.5 $0.00003 $0.00056

Measured 3d ago against content hash fd18a1babe12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

generate-llms 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 3d 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.

.claude/commands/generate-llms.md · 67 lines

What it actually says

/generate-llms — Regenerate llms.txt Files

Regenerate llms.txt (root) and web/public/llms.txt from current source material. Run this after any significant change to the README, profiles list, or agent support.

Source files to read first

  1. README.md — product description, tagline, install command, agent list
  2. docs/llms-full.txt — dense technical summary (authoritative)
  3. profiles/ — list current profiles with ls profiles/ | grep -v '^_'
  4. package.json — current version and npm package name

Root llms.txt — what it must contain

# cuecards (cue)

<one-paragraph description — from README tagline + what-it-does>

## What it solves
<2–3 sentences on the problem>

## Core docs
- [README](<url>) — <purpose>
- [llms-full.txt](<url>) — <purpose>
- [AGENTS.md](<url>) — <purpose>
- [launch.md](<url>) — <purpose>

## Setup guides
- [macOS](<url>)
- [Linux / WSL2](<url>)
- [Windows](<url>)

## Comparisons
- [cue vs claude-code-switcher](<url>)
- [cue vs skillport](<url>)
- [cue vs Kiro Powers](<url>)

## Repository
- GitHub: https://github.com/opencue/cuecards
- npm: https://www.npmjs.com/package/cue-ai
- License: MIT

web/public/llms.txt — condensed version

Same structure as root llms.txt but:

  • Shorter descriptions (1 sentence max per link)
  • Point to deployed URLs (https://opencue.github.io/cuecards/...) where they exist
  • Include the ## GEO files section pointing to content/geo/

After generating

  1. Diff the new files against the previous versions: git diff llms.txt web/public/llms.txt
  2. Verify no URLs were broken (spot-check 3 links)
  3. Commit as: docs: refresh llms.txt [skip ci]

Automation note

This command is also triggered by the nightly discover workflow. If running manually, check the workflow hasn't already run today: git log --oneline --since="24 hours ago" | grep "llms"

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.

  1. 3d ago First seen · 67 lines · 33 tokens per session scan A fd18a1babe12

Subscribe to this mod's changes

generate-llms is a command published in the GitHub repository opencue/cuecards (5 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 565 once invoked, about $0.0002 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.

Related

Other commands, from other repositories

atomic-help

Route a lost user to the right atomic verb, skill, agent, or binary subcommand. Bare invocation reads git state and recommends one next step. Topic keyword or freeform intent → focused pointer. tour → guided walkthrough of the system. Help router, not duplicated docs.

damusix/atomic-claude · 57 tokens

atomic-plan

Write a design doc (concepts, business rules, approaches) and a checkpoint-table spec (contract) for non-trivial work; inline spec only for trivial. Gauges triviality; loops spec authoring with subagents. Human-facing artifact, Mermaid diagrams allowed.

damusix/atomic-claude · 54 tokens

subagent-implementation

Orchestrate implement→review subagent loop until task complete. Reads the approved spec, writes a thin brief to .claude/.scratchpad/, dispatches fresh-context subagents, loops until reviewer signs off, commits per green iteration, then updates repo docs.

damusix/atomic-claude · 53 tokens

follow-up

Review and act on pending reminders. Bare invocation shows all reminders as an indexed list; cron-fired invocation (/follow-up due ) surfaces the specific reminder and waits for a response; /follow-up review lists stale project follow-up entries for per-item disposition (extend/close/promote/skip). Transport-aware…

damusix/atomic-claude · 0 tokens

quick-fix

Run the implement→review subagent loop without the planning phase — for straightforward fixes with a known cause and one obvious approach, regardless of how many files the change spreads across. Skips the spec gate, worktree gate, and finalize ceremony (implementation log, docs, signals) that /subagent-implementation…

damusix/atomic-claude · 112 tokens

documentation

Bootstrap and maintain project documentation surfaces. Two modes: bootstrap (discover doc files, index them in CLAUDE.md) and authoring (scan for unindexed docs, match diff against indexed surfaces, walk stale/incomplete/missing items with Yes/Later/Remind/Skip).

damusix/atomic-claude · 0 tokens