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/Oriolshhh/runware-image-mcpWrote 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/oriolshhh/runware-image-mcp/specialist-routing)<a href="https://agentmods.dev/rules/oriolshhh/runware-image-mcp/specialist-routing"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/specialist-routing/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/rules/oriolshhh/runware-image-mcp/specialist-routing"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/specialist-routing.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 | $0.00013 | $0.00627 |
| Opus 5 | $0.00006 | $0.00313 |
| Sonnet 5 | $0.00003 | $0.00125 |
| Haiku 4.5 | $0.00001 | $0.00063 |
Grade A, and why
specialist-routing 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 5d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: specialist-routing
Specialist Routing
Purpose
Keep a review proportional to risk by convening only the specialists a specific decision actually needs.
When to use it
- In
/councilafter the decision brief exists, before independent review.
Instructions
- Read the brief's facts, constraints, and risk signals.
- Always include architecture and product reviewers.
- Add a specialist only when the brief shows a matching signal:
- security — untrusted input, auth, secrets, filesystem/command execution, dependencies, generated-file ownership, untrusted instructions.
- test — non-trivial behavior, compatibility risk, weak existing coverage.
- operations — deployment, data migration, performance, infra, hard-to-undo.
- ux — user-facing flows, accessibility, states, DX surfaces.
- frontend design — new screens, visual redesign, brand expression, or
hierarchy changes: add
frontend-design-lead; adddesign-system-specialistwhen shared tokens/components or dependencies may change. - frontend verification — substantial interactive UI: plan independent
accessibility-reviewerandvisual-qa-testeracceptance; addmotion-design-revieweronly when motion or gestures are in scope. - data / other — schema/migration/persistence or domain-specific risk.
- Size the council to the risk: trivial/low-risk changes get a minimal roster.
- Always include the devil's advocate for the challenge round.
- Record the reason for each inclusion and each exclusion.
- Apply
model-routingto each selected role. Start from its frontmatter, escalate for task-specific ambiguity/risk, and keep synthesis at least as capable as the strongest judgment being reconciled.
Output format
A routing decision: risk profile (trivial/low/medium/high), selected specialists (each with an evidence-based reason, model tier, and effort), excluded specialists (each with why not), and confirmation of the challenge round.
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.
- 5d ago First seen · 61 lines · 13 tokens per session scan A a7f652233bd9
specialist-routing is a cursor rule published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 627 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 2026-09-03.
Other cursor rules, from other repositories
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.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.