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.
git clone --depth 1 https://github.com/orin-dx/agent-pluginsWrote 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/agents/orin-dx/agent-plugins/exit-gate)<a href="https://agentmods.dev/agents/orin-dx/agent-plugins/exit-gate"><img src="https://agentmods.dev/badge/agents/orin-dx/agent-plugins/exit-gate/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/agents/orin-dx/agent-plugins/exit-gate"><img src="https://agentmods.dev/badge/agents/orin-dx/agent-plugins/exit-gate.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 | $0.00224 | $0.01108 |
| Opus 5.5 | $0.00090 | $0.00443 |
| Sonnet 5.5 | $0.00045 | $0.00222 |
| Haiku 4.5 | $0.00022 | $0.00111 |
Grade A, and why
exit-gate 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 1mo 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Key failure modes:
- Conditional passing: issuing a pass with a note that "the focus-visible criterion could be more precise." That is a fail.
- Any acceptance criterion would require the implementer to make a judgment call about what "accessible" or "correct" means.
- Any state named in the requirement has no criterion and no explicit non_goal.
- Any TBD exists, regardless of how minor.
WHEN the verdict is "fail", THE SYSTEM SHALL include a blockers array where each entry names the specific criterion_id, state, or section and states the exact change required. WHEN retry_count exceeds 3, THE SYSTEM SHALL set verdict to "escalate" and surface the persistent blockers for human review rather than issuing another fail. IF the spec describes a component whose interactive states or accessibility surface are not yet fully enumerated, THE SYSTEM SHALL fail with a blocker naming each missing state or accessibility criterion specifically, rather than a general completeness note.
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.
- 1mo ago Changed · +1 lines 2c0b37980534
- 1mo ago Changed · +6 lines 04fcf9db6a90
- 1mo ago First seen · 36 lines · 224 tokens per session scan A a36432cfe493
exit-gate is an agent published in the GitHub repository orin-dx/agent-plugins (1 stars, last pushed 19d ago), licensed MIT. It adds 224 tokens to every session and 1,108 once invoked, about $0.0009 per session on Opus 5.5. 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 2026-08-31.
Other agents, from other repositories
a11y-checker
Checks React components for missing accessibility attributes. Use when a component is added or changed.
frontend
Frontend frameworks (React/Vue/Angular/Next.js), design systems, accessibility. Use for UI implementation, component work, and responsive design.
ux-reviewer
Master UX and accessibility engineer — Kodelyth. A decade-seasoned product engineer who has shipped interfaces used by hundreds of millions of people at $300B-scale companies. Reviews frontend code with the eye of a UX architect — not by rules, but by deeply understanding how humans think and feel when they use…
DevExpress Report Designer Expert
An expert agent for creating and modifying DevExpress XtraReport layouts in Visual Studio and JetBrains Rider. Works with .Designer.cs files and the Report Designer surface. Use this agent for tasks related to report bands, controls, data binding expressions, styles, or parameters in designer-generated code.
ring:frontend
Senior Frontend Engineer specialized in React/Next.js for financial dashboards and enterprise applications. Expert in App Router, Server Components, accessibility, performance optimization, modern React patterns, and dual-mode UI library support (design-system vs vanilla).
taste-judge
Final-gate taste judge running a 3-lens internal panel over what rubrics cannot capture. Use SPARINGLY on high-stakes work (signature designs, hero copy, brand directions, architecture choices, must-be-right documents), normally after a deliverable has passed two clean verifier sweeps. Also use to rank best-of-N…