jfrog-platform

A set of rules for using the JFrog Platform API, including command-line access, authentication, URLs, and readiness checks.

In plain words
What is it for?
Use it to log in, confirm the target JFrog instance, check readiness, and make platform API calls through the JFrog CLI.
Why use it?
It reduces mistakes when connecting to JFrog, such as using the wrong server, authentication method, or API path.

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/jfrog-platform
Clone the repo
git clone --depth 1 https://github.com/jfrog/ai-agent-examples
Per session 3,083 This file is loaded in full into every session.
When invoked 3,083 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 $0.03083 $0.03083
Opus 5 $0.01541 $0.01541
Sonnet 5 $0.00617 $0.00617
Haiku 4.5 $0.00308 $0.00308

Measured yesterday against content hash 3a4ebb7d794d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

jfrog-platform 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.

Use **`JFROG_URL`** and **`JFROG_ACCESS_TOKEN`** for **manifest URL comparison**, **`curl` fallback**, or legacy snippets—not as the primary auth path when the CLI is configured.
global/rules/jfrog-platform.mdc · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

JFrog Platform Conventions

JFrog CLI and jf api (primary)

Environment variables (secondary / fallback)

Use JFROG_URL and JFROG_ACCESS_TOKEN for manifest URL comparison, curl fallback, or legacy snippets—not as the primary auth path when the CLI is configured.

  • JFROG_URL -- Platform base URL (e.g., https://mycompany.jfrog.io or host-only, depending on skill examples)
  • JFROG_ACCESS_TOKEN -- Bearer token for curl fallback only

Loading from .env file

If the variables are not already set in the environment, look for a .env file in the repository root and source it. The .env file format uses one KEY=VALUE per line (no export keyword needed):

JFROG_URL=https://mycompany.jfrog.io
JFROG_ACCESS_TOKEN=eyJ...

Before operations that still use curl or env-based checks, run this loading snippet when vars are missing:

# Load .env if vars are not already set
if [ -z "$JFROG_URL" ] || [ -z "$JFROG_ACCESS_TOKEN" ]; then
  if [ -f .env ]; then
    set -a
    source .env
    set +a
  fi
fi

Priority: environment variables already set in the shell take precedence over .env values. The .env file is only sourced when one or both vars are missing.

Security: Never commit the .env file to git. Ensure .env is listed in .gitignore.

Read the full file on GitHub · 222 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 · 222 lines · 3,083 tokens per session scan A 3a4ebb7d794d

Subscribe to this mod's changes

jfrog-platform 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 3,083 tokens to every session, about $0.0154 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.