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 ctxt-io/ctxt-agents --skill sharegit clone --depth 1 https://github.com/ctxt-io/ctxt-agentsWrote 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/ctxt-io/ctxt-agents/share)<a href="https://agentmods.dev/skills/ctxt-io/ctxt-agents/share"><img src="https://agentmods.dev/badge/skills/ctxt-io/ctxt-agents/share/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/ctxt-io/ctxt-agents/share"><img src="https://agentmods.dev/badge/skills/ctxt-io/ctxt-agents/share.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 | $0.00074 | $0.01492 |
| Opus 5.5 | $0.00030 | $0.00597 |
| Sonnet 5.5 | $0.00015 | $0.00298 |
| Haiku 4.5 | $0.00007 | $0.00149 |
Grade A, and why
share 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 1mo 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sharing via ctxt.io
ctxt.io turns content into an auto-expiring link in one call. Use the create_context MCP tool (server: ctxt, https://ctxt.io/mcp). The live tool schema and tool results are authoritative — if they differ from this document, follow them.
When to share
- The user asks for a link, or wants to send something to a person, chat, or another agent.
- Output is too long to paste into a chat/issue/commit message.
- The user wants a throwaway rendering of a report, table, or diagram.
Links are bearer-accessible by default — anyone holding the URL can read them; password-protected (Pro) links additionally require the password. Never share secrets, credentials, or private data without the user's explicit say-so. And when the scope of what to publish is at all ambiguous ("share this", "share the output"), state exactly what you intend to publish — a file name, or a one-line description plus size — and get confirmation before sharing.
Choosing ttl
Free: 5m, 30m, 1h (default), 8h, 1d. Paid: 30d costs USD 1 one-time.
Default to 1h unless the user says otherwise. Pick the shortest ttl that plausibly covers the audience's reading window — expiry is the product, not a limitation.
30d / Pro flow: the link is created immediately but in a pending state (lives 1 day unpaid). After the USD 1 payment the link lasts 30 days and Pro options (name slug, password) activate. Payment paths, in order:
- The live tool result is authoritative: if it advertises an agent-payment capability that your platform actually supports, follow it to complete payment programmatically.
- Otherwise — the universal fallback — surface the
payment_urland say plainly that a human has to open it in a browser to finish the checkout.
A free-ttl paste is not a dead end either: a human can later upgrade it to 30-day Pro in a browser via the paste's manage_url (see Result fields). If the user wanted longer than the free tiers but balks at paying now, hand them the manage_url and tell them the upgrade stays available there while the paste is alive.
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.
- 1mo ago Changed · +1 tokens per session 027c1a28f87a
- 2mo ago First seen · 75 lines · 73 tokens per session scan A 97f25014ce23
share is a skill published in the GitHub repository ctxt-io/ctxt-agents (3 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 1,492 once invoked, about $0.0003 per session on Opus 5.5. 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.