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 agentmods add rules/alphabitcore/nexus-gateway/agent-ui-terminologygit clone --depth 1 https://github.com/AlphaBitCore/nexus-gatewayWrote 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/rules/alphabitcore/nexus-gateway/agent-ui-terminology)<a href="https://agentmods.dev/rules/alphabitcore/nexus-gateway/agent-ui-terminology"><img src="https://agentmods.dev/badge/rules/alphabitcore/nexus-gateway/agent-ui-terminology.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00573 |
| Opus 5 | $0.00000 | $0.00287 |
| Sonnet 5 | $0.00000 | $0.00115 |
| Haiku 4.5 | $0.00000 | $0.00057 |
Grade A, and why
agent-ui-terminology 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 6d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent UI terminology (binding)
The Agent UI surfaces what's happening on this device to an end-user, not to a platform admin. Its vocabulary differs from the Control Plane UI on purpose.
Required terminology
- "Traffic event" — every intercepted request. NEVER "AI call", "LLM call", "prompt", or "completion" as the primary noun. (Inside an event detail panel, "prompt" / "completion" labels for body content are fine — but the row itself is a "traffic event".)
- "Allowed / Flagged / Blocked" — outcome verbs map directly to canonical hook decisions.
- "Protection Pause" — user-side temporary intercept pause. Never "disable agent" (the agent is still running).
- "Connection" — Hub link status. Never "platform connection" or "control-plane connection" (too admin-y).
Forbidden terminology in Agent UI
| Don't use | Use instead | Why |
|---|---|---|
| "AI call" / "LLM call" | "Traffic event" / "Request" | Agent is provider-agnostic at this surface |
| "Quota" / "Limit" / "Budget" | (don't surface; not a concept) | Quota is server-side; the agent never tracks or displays it |
| "API key" | "Credential" or omit | API keys live admin-side; on-device user shouldn't reason about them |
| "Tenant" / "Org" | omit unless contextually needed | Admin language; on-device user belongs to their org implicitly |
| "Disable agent" | "Pause protection" | Pause keeps the agent running, just stops intercepting |
| "Inspection" | "Compliance check" / "Hook" | Match admin-side surface naming |
i18n keys
All these terms ride through the i18n pipeline (cross-ref i18n-mandatory.mdc). When you add a key under packages/ui-shared/src/i18n/locales/{en,zh,es}/dashboard.json or the agent-side equivalent, use the required vocabulary.
Enforcement
CI script npm run check:agent-ui-terminology greps the agent UI source + locale files for forbidden tokens. New violations fail CI in strict mode.
Source
- Decision record: memory [[project_agent_ui_ia_redesign]].
- Feature docs:
docs/users/features/agent-ui/overview.md§IA + per-page docs.
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.
- 6d ago First seen · 44 lines · 0 tokens per session scan A b5287f24e9a8
agent-ui-terminology is a cursor rule published in the GitHub repository AlphaBitCore/nexus-gateway (23 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 573 tokens. 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 cursor rules, from other repositories
solana-security
Solana Security Standard (SOL-0XX) - flag and fix Solana/Anchor security bugs.
recipe_author
How to author a recipe in ks-cookbook.
20-phi-redaction-first
PHI redaction first — Presidio gate, token handling, and minimum necessary LLM access for HIPAA workflows.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.