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 access-and-identitygit 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/access-and-identity)<a href="https://agentmods.dev/skills/catpilotai/catpilot-ai-guardrails/access-and-identity"><img src="https://agentmods.dev/badge/skills/catpilotai/catpilot-ai-guardrails/access-and-identity/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/access-and-identity"><img src="https://agentmods.dev/badge/skills/catpilotai/catpilot-ai-guardrails/access-and-identity.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 | $0.00049 | $0.00839 |
| Opus 5 | $0.00024 | $0.00419 |
| Sonnet 5 | $0.00010 | $0.00168 |
| Haiku 4.5 | $0.00005 | $0.00084 |
Grade A, and why
access-and-identity 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 7d 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.
What it actually says
When this applies
- Anyone other than the builder will open the app.
- The person asks to "add a login", "share it with the team", "make it public", or "just password-protect it".
- A tool offers a default such as "anyone with the link", "all users", or one shared password.
- The app shows, edits, or exports information about people, money, or company work.
What to ask
- "Who should be able to open this, and who should not?" Get a named group, not "everyone".
- If they want a login: "Does your company have a sign-in you already use for other tools?" That is the one to use.
What to say
- One sentence: "Whoever can open this can see everything in it, so the audience is a security decision, not a sharing setting."
- On building sign-in from scratch: "Sign-in is one of the parts nobody should invent. Let's use the company's existing sign-in instead."
- On shared passwords: "A password everyone knows is not a lock."
Safe alternative
- Use the company's existing sign-in (often called SSO, single sign-on: one company login that works across many tools) whenever the platform supports it.
- Limit access to the smallest named group that needs it, and add people later rather than removing them later.
- Give people the least they need: viewers who only look, editors who change things, and one or two owners.
- If the platform cannot use company sign-in or named groups, say so, and treat that as a reason to build somewhere else.
Company-specific values
Default access for a new app:
- {{identity_default}}
Never acceptable:
{{identity_never}}
Stop and ask a human if
- Anyone outside the company will use it: customers, vendors, the public.
- The person wants to build or customize sign-in, passwords, or permissions themselves.
- The app decides who may see or change records about other people.
- The platform only offers "anyone with the link" and the app touches company data.
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.
- 7d ago First seen · 91 lines · 49 tokens per session scan A be8f702cf790
access-and-identity is a skill published in the GitHub repository catpilotai/catpilot-ai-guardrails (2 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 839 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.