contributing

A set of repository rules for creating and editing JFrog agent skills, including their metadata, authentication guidance, and contribution records.

In plain words
What is it for?
It helps maintain SKILL.md files, include trigger keywords, follow the JFrog CLI login process, and update CONTRIBUTING.md.
Why use it?
It prevents skill files from drifting into inconsistent formats or unsafe authentication instructions.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/jfrog/ai-agent-examples/contributing
Clone the repo
git clone --depth 1 https://github.com/jfrog/ai-agent-examples
Per session 844 This file is loaded in full into every session.
When invoked 844 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00844 $0.00844
Opus 5 $0.00422 $0.00422
Sonnet 5 $0.00169 $0.00169
Haiku 4.5 $0.00084 $0.00084

Measured yesterday against content hash f293420ad54f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

contributing 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 yesterday.

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.

- **Authentication section** near the top that states: **primary** auth is **JFrog CLI 2.100.0+** with **`jf config`** and **`jf api <path>`** (no manual `Authorization` header in the happy path). Include the **`Authoriz
platform-features/rules/contributing.mdc · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contributing to JFrog Skills Repo

When creating or editing skill files in this repository, follow these conventions so skills stay consistent and maintainable.

SKILL.md requirements

  • YAML frontmatter at the top with:
    • name: Human-readable skill name (e.g. "JFrog Artifactory").
    • description: One or two sentences including trigger keywords (e.g. "Triggers on mentions of artifactory, repository, artifact, deploy, ...").
  • Authentication section near the top that states: primary auth is JFrog CLI 2.100.0+ with jf config and jf api <path> (no manual Authorization header in the happy path). Include the Authorization: Bearer $JFROG_ACCESS_TOKEN pattern only for curl fallback. Auth per skills/jfrog-cli/login-flow.md and skills/jfrog-cli/jf-api-patterns.md: (1) install CLI and verify version, (2) resolve the active environment from jf config show, asking the user which env if multiple are saved, (3) show URLs from jf config show and ask the user to confirm the target platform (one question at a time), (4) run jf api /artifactory/api/v1/system/readiness after confirmation, (5) if no credentials exist, agent-driven web login — JFrog URL, session, login link, token saved via jf config add.
  • Official Documentation section at the bottom with 2–5 links to JFrog Help / REST API / CLI docs.

API and URL placeholders

  • Preferred examples: jf api /artifactory/api/... (path only; credentials from jf config). Add --server-id when multiple servers exist.
  • Fallback examples: use $JFROG_URL in full URL patterns (e.g. https://$JFROG_URL/artifactory/api/...) with Authorization: Bearer $JFROG_ACCESS_TOKEN for curl when the CLI is unavailable.
  • Do not hardcode specific JFrog hostnames in skill content.

Reference files

  • API and command catalogs live in *-reference.md files (e.g. rest-api-reference.md, api-reference.md, aql-reference.md, events-reference.md).
  • Keep long endpoint or command lists in reference files; keep SKILL.md focused on flow and when to use what.

Read the full file on GitHub · 45 lines

Changes

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.

  1. yesterday First seen · 45 lines · 844 tokens per session scan A f293420ad54f

Subscribe to this mod's changes

contributing 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 844 tokens to every session, about $0.0042 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.