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 catpilotai/catpilot-ai-guardrails --skill sharing-and-publishinggit clone --depth 1 https://github.com/catpilotai/catpilot-ai-guardrailsWrote 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/catpilotai/catpilot-ai-guardrails/sharing-and-publishing)<a href="https://agentmods.dev/skills/catpilotai/catpilot-ai-guardrails/sharing-and-publishing"><img src="https://agentmods.dev/badge/skills/catpilotai/catpilot-ai-guardrails/sharing-and-publishing/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/catpilotai/catpilot-ai-guardrails/sharing-and-publishing"><img src="https://agentmods.dev/badge/skills/catpilotai/catpilot-ai-guardrails/sharing-and-publishing.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 | $0.00051 | $0.00901 |
| Opus 5 | $0.00026 | $0.00451 |
| Sonnet 5 | $0.00010 | $0.00180 |
| Haiku 4.5 | $0.00005 | $0.00090 |
Grade A, and why
sharing-and-publishing 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 4d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When this applies
- The person is about to share a link, publish, embed, export, send a screenshot or recording, or post a result in a chat or document.
- They ask "can I send this to them?" about a vendor, a customer, a wide channel, or the public.
- The app or its output includes names, emails, amounts, internal names, or anything pulled from company systems.
What to ask
- "Who will see this, and is there anything in it they should not see?"
- Before a wider release: "Who tried it first, and what happened?"
What to say
- One sentence: "Sharing is the moment a private draft becomes a public fact, so check the audience and the contents before the click."
- On screenshots: "A screenshot carries everything on the screen, including the rows you were not thinking about."
- On public links: "A link nobody has posted yet is still public. Being hard to find is not a lock."
Safe alternative
- Start with a private preview: a few named people, one real task for them to try, and a way to report problems.
- Before sharing, read the output as the recipient would. Remove real names, amounts, and internal details unless the recipient is entitled to them.
- Use the platform's audience settings (named people or groups) instead of public links.
- If a settings file already grants public or anyone-with-the-link access, say so in the first sentence of your reply and name who can change it, before the link goes anywhere. If the person asked you to leave the file alone, leave it alone and still say it.
- Keep the last working version, and decide in advance what would make you turn the new one off.
- After sharing, watch a few simple signs: a save fails, a number is wrong, someone sees more than they should.
Company-specific values
Never acceptable when sharing:
{{identity_never}}
Stop and ask a human if
- The recipient is outside the company and the content came from company systems.
- The output includes customer, employee, payment, or health information.
- The person wants to make something public, embed it on a website, or post it in a large channel.
- Something has already been shared too widely. Say so, suggest reporting it to {{owner}}, and help unshare it first.
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.
- 4d ago Changed · +4 lines f9762dd69c92
- 7d ago First seen · 88 lines · 51 tokens per session scan A 91dbaa45df67
sharing-and-publishing is a skill published in the GitHub repository catpilotai/catpilot-ai-guardrails (2 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 901 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 2026-09-14.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
baoyu-article-illustrator
Article illustrations: type × style × palette consistency.
flash-attention
Speed up long-sequence transformer training and inference.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
duckduckgo-search
Free keyless web, news, and image search via ddgs.
simpo
Reference-free preference alignment, simpler than DPO.