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/j4flmao/agent-skillsWrote 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/j4flmao/agent-skills/routing)<a href="https://agentmods.dev/rules/j4flmao/agent-skills/routing"><img src="https://agentmods.dev/badge/rules/j4flmao/agent-skills/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/j4flmao/agent-skills/routing"><img src="https://agentmods.dev/badge/rules/j4flmao/agent-skills/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 | $0.00858 | $0.00858 |
| Opus 5.5 | $0.00343 | $0.00343 |
| Sonnet 5.5 | $0.00172 | $0.00172 |
| Haiku 4.5 | $0.00086 | $0.00086 |
Grade A, and why
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 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Routing — 542 skills
No match -> skills/core/master-orchestrator/SKILL.md. Detect stack then route.
Keywords
core/ onboarding/context-compressor planning/ brief/prd/adr/story/roadmap/pitch-deck/market-analysis/bpmn-modeling/bdd-atdd backend/ {stack}/php + universal (oop/api/db/auth/testing/grpc/websocket/mq/caching/rate-limit/load-test/api-gateway/graphql/bg-jobs/search/streaming/file-storage/feature-flags/i18n/logging/cqrs/event-sourcing/saga/outbox/authorization) + firebase/supabase frontend/ {framework} + universal (state/a11y/performance/testing/tailwind/storybook/pwa/seo/animation/form/data-fetching/bundler/img-opt/theming) + remix/astro/solidjs/qwik/svelte-core mobile/ ios/android/flutter/react-native/kotlin-multiplatform/ionic-capacitor/dotnet-maui + universal (patterns/testing/performance/security/networking/storage/deployment/push/iap/crash/deep-linking/offline/biometrics/maps/camera/analytics) devops/ docker/k8s/terraform/helm/ansible/github-actions/gitops/vault/aws/serverless/monorepo/dep-mgmt/api-doc/argo-cd/azure/gcp/chaos/service-mesh/finops/backup-dr/db-migration/dataops/mlops/k8s-for-data/cloud-cost/pulumi/crossplane/gitlab-ci/circleci/kubernetes-autoscaling/apm-observability/cilium-ebpf/opentelemetry/oracle-cloud/digitalocean/ibm-cloud/alibaba-cloud/hetzner dev-loop/ review/debug/refactor/git/pr-writer/dev-container/tech-debt/api-client management/ pm/ba/qa/qc/security/okr-kpi/sprint-retro/risk/agile-scrum-kanban/team-topology/change-management enterprise/ compliance/multi-tenant/integration/data-governance/sla/legacy/identity/cost/togaf-zachman/itil/vendor/architecture-governance product/ analytics/ab-test/user-research/growth/pricing/gtm/onboarding/prioritization/customer-journey/persona ml/ experiment-tracking/classical-ml/deep-learning/feature-engineering/hyperparameter-tuning/model-evaluation/model-interpretability/time-series/nlp/computer-vision/recommender/anomaly-detection/ml-pipeline/feature-store/model-serving ai/ prompt-engineering/rag/llm-ops/vector-database/ai-agents/ai-evals/model-training/embeddings/multimodal/ai-safety/ai-testing/ai-cost-optimization/langchain/mcp/ai-observability security/ sast-dast/sbom/secrets-management/container-security/api-security/data-security/zero-trust/cspm/penetration-testing/iam-governance/rbac/abac quality/ e2e-testing/visual/load-testing/contract-testing/unit-testing/integration-testing/property-based/exploratory/acceptance/regression/smoke data/ etl/warehouse/streaming/bi/data-quality/distributed-storage/distributed-compute/data-lake/lakehouse/batch-processing/workflow-orchestration/cdc/data-replication/data-platform/data-catalog/data-observability/data-contracts/data-mesh/data-versioning/data-api/data-virtualization/schema-registry/relational-database/nosql/graph-database/search-engine/clean-room/cost-optimization/formats/lineage/pipeline-cicd/testing/reverse-etl/data-strategy/dimensional-modeling data-science/ statistical-analysis/experimentation/causal-inference/analytics-engineering blockchain/ core/cryptography/ethereum/bitcoin/patterns/application/web3/testing/infrastructure/security/management/solana/defi/cross-chain/zk/data-indexing
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 First seen · 28 lines · 858 tokens per session scan A 6b9d19134d30
routing is a cursor rule published in the GitHub repository j4flmao/agent-skills (33 stars, last pushed 10d ago), licensed MIT. It adds 858 tokens to every session, about $0.0034 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 2026-09-06.
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.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
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.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).