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.
git clone --depth 1 https://github.com/oalders/kitchen-sinkWrote 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/commands/oalders/kitchen-sink/geo-review)<a href="https://agentmods.dev/commands/oalders/kitchen-sink/geo-review"><img src="https://agentmods.dev/badge/commands/oalders/kitchen-sink/geo-review/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/commands/oalders/kitchen-sink/geo-review"><img src="https://agentmods.dev/badge/commands/oalders/kitchen-sink/geo-review.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 | $0.00036 | $0.03971 |
| Opus 5 | $0.00018 | $0.01985 |
| Sonnet 5 | $0.00007 | $0.00794 |
| Haiku 4.5 | $0.00004 | $0.00397 |
Grade A, and why
geo-review scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sSL "$SITE$path" -o "$CORPUS/default$slug.html" How it starts
The opening of the file, as written. The whole thing — 393 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEO Review
Overview
GEO (Generative Engine Optimization) review for how LLMs and AI answer engines (ChatGPT, Claude, Perplexity, Google AI Overviews) discover, extract, and cite content.
GEO operates on two distinct mechanisms, and they fail differently:
| Layer | Question it answers | Unit of analysis | Fails via |
|---|---|---|---|
| Extraction | Can a model cleanly lift and cite this page? | The page / the diff | Buried answers, unstructured claims, missing schema |
| Entity | Would a model recommend this site unprompted? | The whole site, over time | Contradictory claims across pages, weak or ambiguous brand identity |
Most GEO tooling only checks extraction, because extraction is visible in a changeset. Entity defects are invisible to any diff — they emerge when one page grows and another doesn't. This command therefore has two modes. Run diff mode at PR time and site mode on a schedule.
Run /seo-review alongside this for ranked-link visibility.
When to Use
Diff mode — use when:
- Adding or modifying content pages, blog posts, docs, or marketing copy
- Changing structured data (JSON-LD)
- Updating author bios, About pages, or other E-E-A-T surfaces
- Modifying
robots.txtrules for AI crawlers - Adding factual claims, statistics, or original research
- Restructuring content into Q&A, lists, or tables
Site mode — use when:
- On a schedule (monthly/quarterly), regardless of what changed
- Before a rebrand, repositioning, or major scope expansion
- After the product has outgrown its original description
- Whenever the site's scale, geography, or offering has changed materially since the About page was written
- An external GEO audit returned a finding you can't reproduce from a single page
Don't use when:
- Pure backend logic with no user-facing content
- Internal admin pages explicitly excluded from LLM crawling
Step 1: Determine Mode
If the user specified a mode, use it. Otherwise infer: a git range or PR context in conversation implies diff mode; a bare URL or "audit the site" implies site mode. If it's ambiguous, ask — the two modes produce very different reports.
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.
- 10d ago First seen · 393 lines · 36 tokens per session scan A ab9b4e3740e8
geo-review is a command published in the GitHub repository oalders/kitchen-sink (4 stars, last pushed 10d ago), licensed MIT. It adds 36 tokens to every session and 3,971 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.