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 madebypan/chatgpt-bookmark-site --skill connect-bookmark-sitegit clone --depth 1 https://github.com/madebypan/chatgpt-bookmark-siteWrote 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/madebypan/chatgpt-bookmark-site/connect-bookmark-site)<a href="https://agentmods.dev/skills/madebypan/chatgpt-bookmark-site/connect-bookmark-site"><img src="https://agentmods.dev/badge/skills/madebypan/chatgpt-bookmark-site/connect-bookmark-site/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/skills/madebypan/chatgpt-bookmark-site/connect-bookmark-site"><img src="https://agentmods.dev/badge/skills/madebypan/chatgpt-bookmark-site/connect-bookmark-site.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 | $0.00057 | $0.00684 |
| Opus 5 | $0.00028 | $0.00342 |
| Sonnet 5 | $0.00011 | $0.00137 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
connect-bookmark-site 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connect Bookmark Site
Connect the user's Codex installation directly to their own Site. Use OAuth; never request, copy, print, or store a Site token, authorization code, cookie, API key, or owner email.
Connect
-
Obtain the user's Bookmark Site URL. Accept either its HTTPS origin or its
/mcpURL. Do not ask again when it is already present in the task. -
Normalize the endpoint:
- Reject URLs containing a username, password, query, or fragment.
- Require
https://, except that loopbackhttp://localhost,127.0.0.1, or[::1]is valid for local development. - Convert an origin URL to
<origin>/mcp. Reject unrelated non-root paths.
-
Verify the deployment without credentials. Fetch
<origin>/.well-known/oauth-protected-resourceand require JSON whoseresourceequals the normalized MCP URL and whose authorization server is the same origin. A401from/mcpis expected before login. -
Require the
codexCLI. Inspect the existing entry with:codex mcp get bookmark-site --jsonIf the entry already uses the normalized URL, keep it. If it points elsewhere, state the old and new origins and ask before replacing it because replacement clears that connection's stored OAuth session. After confirmation, run
codex mcp logout bookmark-siteandcodex mcp remove bookmark-site; tolerate a missing login. -
Add the remote server when needed:
codex mcp add bookmark-site --url https://example.chatgpt.site/mcpSubstitute only the verified endpoint; never use the example URL literally.
-
Start the OAuth flow:
codex mcp login bookmark-site --scopes knowledge:readPause while the user completes ChatGPT sign-in and approves access in the browser. Never ask them to paste anything back into the conversation.
-
Confirm
codex mcp get bookmark-site --jsonshows the expected URL. Tell the user to start a new task so Codex loads the newly connected tools, then test withlist_recent_bookmarks.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 49 lines · 57 tokens per session scan A da50c168a8d1
connect-bookmark-site is a skill published in the GitHub repository madebypan/chatgpt-bookmark-site (4 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 684 once invoked, about $0.0003 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 2026-08-31.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…