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 RiggdAI/uniqent --skill escalation-policygit clone --depth 1 https://github.com/RiggdAI/uniqentWrote 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/riggdai/uniqent/escalation-policy)<a href="https://agentmods.dev/skills/riggdai/uniqent/escalation-policy"><img src="https://agentmods.dev/badge/skills/riggdai/uniqent/escalation-policy/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/riggdai/uniqent/escalation-policy"><img src="https://agentmods.dev/badge/skills/riggdai/uniqent/escalation-policy.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 | $0.00023 | $0.00267 |
| Opus 5 | $0.00012 | $0.00133 |
| Sonnet 5 | $0.00005 | $0.00053 |
| Haiku 4.5 | $0.00002 | $0.00027 |
Grade A, and why
escalation-policy 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 12d 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
Escalation Policy
- Escalate immediately (do not draft a reply first) when any of the following are true:
- The customer has used legal language or mentioned filing a complaint, lawsuit, or regulatory body.
- The inquiry involves a potential security incident (unauthorized account access, data concern).
- The customer has been abusive or threatening in this or a previous interaction.
- Escalate after one failed AI attempt when:
- The AI-drafted reply was rejected or the customer is still unresolved after two exchanges.
- The required action (e.g. manual refund override, account unlock) is outside the AI's authority.
- When escalating, draft a brief internal handoff note for the human agent: customer name/ID, issue summary, what was already tried, and urgency level.
- Inform the customer in their language that a human agent will follow up within the high-urgency SLA (30 minutes) or standard SLA (2 hours), depending on urgency. Do not name the agent.
- Mark the ticket status as "escalated" and stop further AI replies until the human resolves or re-opens it.
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.
- 12d ago First seen · 18 lines · 23 tokens per session scan A 94532b7cb89b
escalation-policy is a skill published in the GitHub repository RiggdAI/uniqent (15 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 267 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
himalaya
CLI to manage emails via IMAP/SMTP. Use himalaya to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
obsidian
Read, search, and create notes in the Obsidian vault.
apple-reminders
Manage Apple Reminders via remindctl CLI (list, add, complete, delete).
apple-notes
Manage Apple Notes via the memo CLI on macOS (create, view, search, edit).
notion
Notion API for creating and managing pages, databases, and blocks via curl. Search, create, update, and query Notion workspaces directly from the terminal.
google-workspace
Gmail, Calendar, Drive, Contacts, Sheets, and Docs integration via gws CLI (googleworkspace/cli). Uses OAuth2 with automatic token refresh via bridge script. Requires gws binary.