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.
npx skills add sitegpt/agent-skills --skill sitegpt-cligit clone --depth 1 https://github.com/sitegpt/agent-skillsWrote 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/skills/sitegpt/agent-skills/sitegpt-cli)<a href="https://agentmods.dev/skills/sitegpt/agent-skills/sitegpt-cli"><img src="https://agentmods.dev/badge/skills/sitegpt/agent-skills/sitegpt-cli.svg" alt="Measured on agentmods" 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 | $0.00059 | $0.11987 |
| Opus 5 | $0.00030 | $0.05993 |
| Sonnet 5 | $0.00012 | $0.02397 |
| Haiku 4.5 | $0.00006 | $0.01199 |
Grade A, and why
sitegpt-cli 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 8d 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 -sIL "https://example.com" | grep -iE '^HTTP/|^location:' How it starts
The opening of the file, as written. The whole thing — 873 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SiteGPT CLI
Use the SiteGPT CLI to manage SiteGPT accounts and chatbots from a terminal or agent environment. Prefer CLI commands for direct operations, scripting, file uploads, and reliable terminal output.
The installed command is sitegpt.
SiteGPT also publishes an agent auth discovery file at
https://sitegpt.ai/auth.md. Use it when an agent environment wants a
standard, machine-readable description of the anonymous onboarding registration
flow. The CLI commands below remain the preferred implementation path when a
terminal is available.
Prerequisite
Check whether the CLI is installed before starting:
sitegpt --version
If sitegpt is missing, ask the user before installing it:
npm install -g @sitegpt/cli
Agent Operating Mode
You own the outcome: a working, branded, accurate chatbot the human is glad to claim — not a list of commands run. Act like a SiteGPT implementation engineer.
- Understand the business from its website, docs, audience, and support needs.
- Resolve the canonical website URL first and reuse it everywhere (see "Resolve The Canonical Website URL First").
- Build a discovery brief and ask it before you create or train the chatbot — use case, industry, audience, persona, primary goal, escalation (see "Build A Discovery Brief First"). Creating the chatbot and ingesting knowledge before you ask reads as never having asked, even if you ask afterward.
- Create or update the right SiteGPT resources through the CLI; prefer
--jsonfor IDs and status; parallelize independent work after required IDs exist. - Treat the website as messy: handle bare/non-canonical domains, JS-rendered pages, anti-bot blocks, and missing sitemaps without giving up (see "Robustness And Recovery").
- The value moment is a correct answer to a question the human did not script. Do not hand over a preview until you have verified that (see "The Aha Test").
- Stay visible on anything longer than a few seconds, and finish with a crisp handoff: what you built, test questions to try, and the claim/dashboard link.
- Never invent company facts, pricing, policies, or capabilities; never echo tokens; confirm before anything destructive.
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.
- 8d ago First seen · 873 lines · 59 tokens per session scan A 60ee5b78ece4
sitegpt-cli is a skill published in the GitHub repository sitegpt/agent-skills (0 stars, last pushed 15d ago), licensed MIT. It adds 59 tokens to every session and 11,987 once invoked, about $0.0003 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…