A command that checks whether a project's Generative Engine Optimisation (GEO) files accurately describe it for AI search and answer systems.

Use it to audit llms.txt files and other GEO content against the project's documentation and package information.

It catches outdated or inconsistent installation details, links, metadata, feature lists, and FAQ content that could make the project harder to discover or cite correctly.

audit-geo — Command for Claude Code by opencue

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.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/opencue/cuecards/audit-geo.svg)](https://agentmods.dev/commands/opencue/cuecards/audit-geo)

Your own site

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

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 637 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.

Model	Per session	Once invoked
Fable 5.1	$0.00024	$0.00637
Opus 5	$0.00012	$0.00318
Sonnet 5	$0.00005	$0.00127
Haiku 4.5	$0.00002	$0.00064

Measured 3d ago against content hash e9b610f6da53, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

audit-geo 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/audit-geo.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/audit-geo — GEO Health Check for cuecards

Audit cuecards' Generative Engine Optimisation (GEO) layer for accuracy and completeness. GEO = making Cue easy for ChatGPT, Perplexity, Google AI Overviews, and similar systems to understand, summarise, and cite correctly.

What to check

1. llms.txt accuracy (root)

Version/install command is current: grep "npm install" llms.txt matches current npm package
Supported agent count matches docs/llms-full.txt

2. web/public/llms.txt accuracy

Consistent with root llms.txt
All linked GitHub URLs resolve (spot-check 3)

3. content/geo/entity-profile.json

Valid JSON: python3 -m json.tool content/geo/entity-profile.json > /dev/null
@type includes SoftwareApplication
featureList count ≥ 8
keywords list ≥ 8 terms
description field matches README tagline (no drift)

4. content/geo/brand-facts.md

Agent count in "Supported agents" section matches docs/llms-full.txt
Install commands are syntactically valid bash
Token cost claim (10–25×) matches README claim

5. content/geo/answer-engine-faq.md

Every answer is ≥ 2 sentences (too short = not citation-worthy)
Install commands match current package.json package name
No questions reference outdated file names (e.g. .cue-profile should now be .cue.profile)

6. content/geo/ai-discovery-map.yml

All url: values use the correct GitHub org (opencue/cuecards)
No dead paths referenced (check do_not_scrape list is still accurate)

7. Consistency cross-check

Product name: "cuecards" (lowercase) used consistently — not "CUE" or "Cue" as primary
npm package: cue-ai consistent across all geo files
Repository: https://github.com/opencue/cuecards consistent

Report format

File	Status	Issues
llms.txt (root)	✅/❌	...
web/public/llms.txt	✅/❌	...
entity-profile.json	✅/❌	...
brand-facts.md	✅/❌	...
answer-engine-faq.md	✅/❌	...
ai-discovery-map.yml	✅/❌	...
Cross-file consistency	✅/❌	...

Read the full file on GitHub · 61 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.

3d ago First seen · 61 lines · 24 tokens per session scan A e9b610f6da53

Subscribe to this mod's changes

audit-geo is a command published in the GitHub repository opencue/cuecards (5 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 637 once invoked, about $0.0001 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.

Analytics and metrics Claude Code Marketing and SEO ai-agents ai-coding anthropic claude cli

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

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).