Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sudhasubash1990/Salesforce-Enterprise-skillsnpx agentmods add rules/sudhasubash1990/salesforce-enterprise-skills/routingWrote 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/sudhasubash1990/salesforce-enterprise-skills/routing)<a href="https://agentmods.dev/rules/sudhasubash1990/salesforce-enterprise-skills/routing"><img src="https://agentmods.dev/badge/rules/sudhasubash1990/salesforce-enterprise-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/sudhasubash1990/salesforce-enterprise-skills/routing"><img src="https://agentmods.dev/badge/rules/sudhasubash1990/salesforce-enterprise-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 | $0.03022 | $0.03022 |
| Opus 5 | $0.01511 | $0.01511 |
| Sonnet 5 | $0.00604 | $0.00604 |
| Haiku 4.5 | $0.00302 | $0.00302 |
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 10d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Routing
Decision tree for routing user requests to the correct skill, playbook, or template.
Layer 0 — Framework Core (All SEACF Modules)
Before BA or QE deep work, load Tier-0 contracts from framework-core/:
framework-core/README.mdframework-core/orchestration/request-router.mdframework-core/orchestration/context-manager.mdframework-core/governance/quality-standards.md
Router separation:
| Layer | Owner | Role |
|---|---|---|
framework-core/orchestration/ |
SEACF Core | Cross-module contracts (which module, loading tiers) |
.cursor/rules/routing.mdc + scripts/retrieve_context.py |
BA | BA Layer 2 file-bundle retriever (BA-scoped; QE keywords redirect) |
salesforce-quality-engineering/enterprise-orchestrator/ |
QE Module 2 | Intra-QE sprint capability routing |
Layer 2 Retriever (BA — Run First for BA Tasks)
For any BA task, run the deterministic retriever BEFORE loading files manually:
python scripts/retrieve_context.py --query "<the user's request>"
It always includes Tier-0 Framework Core. It matches BA routing rules plus the frontmatter metadata graph and returns the exact context bundle to load. If the query is QE-dominated, it returns a qe-redirect bundle pointing at salesforce-quality-engineering/ — do not continue on the BA path. Use --json for machine-readable output and --list-tasks to see supported routes.
If the retriever reports no task rule matched, fall back to the manual decision tree below and ask one clarifying question about deliverable type and industry context.
The keyword tables below remain the source of truth for maintaining the BA retriever: when adding a BA route here, add the same rule to scripts/retrieve_context.py (guarded by scripts/test_retrieve_context.py).
Primary Router
User Request
│
├─ Tier-0 Framework Core (all SEACF) ───────────► framework-core/README.md + request-router.md
│
├─ QE / test strategy / defect / automation / Sev1 / hypercare / CQO advisory
│ └─► salesforce-quality-engineering/skill.md + enterprise-orchestrator/
│
├─ Any BA task (start) ─────────────────────────► skill.md + brain/identity.md
│
├─ Analyze requirement / recommend solution ────► brain/reasoning-framework.md
│ └─ brain/decision-framework.md + playbooks/fit-gap-analysis.md
│
├─ Requirements / BRD / business needs ──────────► skill.md + brain/output-framework.md
│ └─ templates/brd-template.md
│
├─ Functional requirements / FRD ───────────────► brain/output-framework.md
│ └─ templates/frd-template.md
│
├─ User stories / backlog / acceptance criteria ► skill.md + brain/output-framework.md
│ └─ templates/user-story-template.md
│
├─ RAID / risks / assumptions / dependencies ───► templates/raid-log-template.md
│
├─ Traceability / RTM ──────────────────────────► templates/traceability-matrix-template.md
│
├─ Discovery / workshops / stakeholder interviews ► brain/enterprise-behaviors.md
│ └─ playbooks/discovery-workshop-playbook.md + templates/workshop-agenda-template.md
│
├─ Fit-gap / solution options / build vs buy ───► brain/decision-framework.md
│ └─ playbooks/gap-analysis-playbook.md + solution-recommendation-playbook.md
│
├─ Validate BA draft / review BA artifact ──────► brain/validation-framework.md
│ └─ brain/anti-hallucination.md + checklists.md
│
├─ UAT / BA test scenarios / sign-off ──────────► playbooks/uat-playbook.md + uat-planning-playbook.md
│
├─ KPI definition / baselines / target outcomes ► templates/kpi-baseline-template.md
│
├─ Change management / adoption / upskilling ───► playbooks/change-management-playbook.md
│ └─ templates/comms-upskilling-plan-template.md
│
├─ Digital transformation / reinvention strategy ► playbooks/digital-transformation-strategy-playbook.md
│
├─ Industry-specific context ───────────────────► scenarios/<industry>.md
│
├─ Interview prep / hiring / mock interview / capability assessment ► interview-guide/interview-index.md
│ └─ interview-guide/<topic>.md per round type
│
├─ Prompt engineering for BA tasks ─────────────► prompts.md
│
└─ Repository / governance / standards ─────────► docs/ or shared/
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.
- 10d ago First seen · 231 lines · 3,022 tokens per session scan A 890d0e7d7e2d
routing is a cursor rule published in the GitHub repository sudhasubash1990/Salesforce-Enterprise-skills (3 stars, last pushed 22d ago), licensed MIT. It adds 3,022 tokens to every session, about $0.0151 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 2026-08-31.
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.