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/jfrog/ai-agent-examples/onboarding-workflowgit clone --depth 1 https://github.com/jfrog/ai-agent-examplesWhat 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 | $0.04012 | $0.04012 |
| Opus 5 | $0.02006 | $0.02006 |
| Sonnet 5 | $0.00802 | $0.00802 |
| Haiku 4.5 | $0.00401 | $0.00401 |
Grade A, and why
onboarding-workflow scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
When a local manifest file is found (e.g., `jfrog-manifest.yaml`), **always compare** its `jfrog.url` value against the **URL of the JFrog instance the user confirmed** from `jf config show` (or against `$JFROG_URL` from How it starts
The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboarding Workflow Guidance
Skill Chain Order
Always follow this sequence when onboarding a project:
Pre-project step (run once before any projects):
0. Detect existing patterns -- after prerequisites pass, query the platform for existing projects and repositories via the detect-existing-patterns skill. If existing naming patterns are found that differ from the standard convention, present both the detected and standard options with concrete examples and let the user choose. The chosen naming_pattern applies to all projects in the current onboarding run. If the platform is empty or existing repos already follow the standard pattern, skip the question and use the standard pattern.
Per-project steps (repeat for each project in the manifest):
- Provision project -- create JFrog project if it does not exist
- Create repositories -- from ecosystems (auto-generated trios), custom
repositorieslist, or both (smart merge); conditionally enable Xray indexing and Curation (curated: trueflag) based on manifest settings. Pass thenaming_patternfrom step 0 to control how ecosystem-generated repo names are constructed. - Add members -- users and groups with appropriate roles
- OIDC setup -- configure OIDC provider and identity mappings (controlled by
github.oidc_setupin manifest; iftrueand subscription does not support it, abort) - Configure package managers -- update configs in the GitHub repos for local dev
- Configure CI workflows -- modify GitHub Actions for Artifactory integration (uses OIDC if
github.oidc_setup: true, otherwise secrets-based auth)
Post-project steps (run once after all projects):
7. Curation policies -- if any project has curation.enabled: true, invoke jfrog-curation-onboarding in automated mode to create the 8 standard curation policies (Block Malicious + 7 dry-run). Uses all_repos scope when all projects have curation enabled, or specific_repos scope when only some do. Notification email comes from jfrog.curation.notification_email (or per-project override).
8. Persist manifest -- store final manifest to the configured state backend (Artifactory or git)
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.
- 2d ago First seen · 218 lines · 4,012 tokens per session scan A d5a0d914d287
onboarding-workflow is a cursor rule published in the GitHub repository jfrog/ai-agent-examples (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 4,012 tokens to every session, about $0.0201 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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
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.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.