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 third-party-servicesgit 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/third-party-services)<a href="https://agentmods.dev/skills/catpilotai/catpilot-ai-guardrails/third-party-services"><img src="https://agentmods.dev/badge/skills/catpilotai/catpilot-ai-guardrails/third-party-services/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/third-party-services"><img src="https://agentmods.dev/badge/skills/catpilotai/catpilot-ai-guardrails/third-party-services.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 | $0.00048 | $0.00824 |
| Opus 5 | $0.00024 | $0.00412 |
| Sonnet 5 | $0.00010 | $0.00165 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
third-party-services 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When this applies
- The person wants to connect the app to a service the company has not clearly approved: a free API, a plugin, a browser extension, a new AI provider, a marketplace connector, an automation platform.
- A tool suggests installing something to make a task easier.
- The person is signing up for a new account "just to try it".
What to ask
- "Is this service on your company's approved list, or is it new?"
- If it is new: "What would it receive, and where does that information go?"
What to say
- One sentence: "Every new service is a new place your company's information lives, and someone has to be responsible for it."
- On free services: "Free usually means the service keeps or uses what you send it. That may be fine for pretend data and not fine for real data."
- On plugins and extensions: "A plugin can read everything the app can read. Installing one is like giving someone a key."
Safe alternative
- Prefer services the company has already approved; the approved option is usually already connected somewhere.
- Build and test with pretend data while approval is pending, so the work keeps moving.
- Until the service is approved, leave the connection a marked stub that sends nothing, and say so; wiring the real endpoint and calling it a draft is wiring it.
- Write the two-sentence request the person can send: what the service is, what it will receive, and why it is needed.
- Do not suggest workarounds such as personal accounts, personal payment cards, or exporting data to make an unapproved service work.
Company-specific values
Approved services:
{{approved_services}}
Needs review before use:
{{services_needs_review}}
Stop and ask a human if
- The service would receive customer, employee, payment, or health data.
- The service needs a payment method, a contract, or company credentials.
- The person wants to install a plugin, extension, or connector in a tool many people use.
- The service is a new AI provider or model endpoint.
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 · +3 lines 9fa5de2f59df
- 7d ago First seen · 87 lines · 48 tokens per session scan A fb5767bb30ab
third-party-services is a skill published in the GitHub repository catpilotai/catpilot-ai-guardrails (2 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 824 once invoked, about $0.0002 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.