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/jfrog/ai-agent-examplesnpx agentmods add skills/jfrog/ai-agent-examples/jfrog-curationWrote 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/skills/jfrog/ai-agent-examples/jfrog-curation)<a href="https://agentmods.dev/skills/jfrog/ai-agent-examples/jfrog-curation"><img src="https://agentmods.dev/badge/skills/jfrog/ai-agent-examples/jfrog-curation/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/skills/jfrog/ai-agent-examples/jfrog-curation"><img src="https://agentmods.dev/badge/skills/jfrog/ai-agent-examples/jfrog-curation.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 | $0.00058 | $0.01581 |
| Opus 5.5 | $0.00023 | $0.00632 |
| Sonnet 5.5 | $0.00012 | $0.00316 |
| Haiku 4.5 | $0.00006 | $0.00158 |
Grade A, and why
JFrog Curation scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> **API transport:** Prefer **`jf api`** (JFrog CLI 2.100.0+). See [jf-api-patterns.md](../jfrog-cli/jf-api-patterns.md) (path-only URLs; auth from `jf config`). Examples using **`curl`** with `$JFROG_URL` + bearer token How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API transport: Prefer
jf api(JFrog CLI 2.100.0+). See jf-api-patterns.md (path-only URLs; auth fromjf config). Examples usingcurlwith$JFROG_URL+ bearer token are fallback when the CLI is missing or below 2.100.0.
JFrog Curation Skill
Authentication
All requests require an access token via the Authorization header:
Authorization: Bearer $JFROG_ACCESS_TOKEN
Base URL: https://$JFROG_URL/curation/api/...
When authentication is needed, follow the login-flow.md procedure to resolve the active JFrog environment. The jf CLI is required and will be installed automatically if missing. The agent checks saved credentials via jf config show and asks which environment to use if multiple are saved. If none exist, the agent drives the web login flow and saves credentials via jf config add.
Pre-flight: Before operations, verify Curation is available:
GET $JFROG_URL/curation/api/v1/system/ping(expect HTTP 200). If unavailable, inform the user that Curation is not deployed on this instance and stop.
Core Concepts
Curation is a package firewall that intercepts downloads from remote repositories. Before a package reaches Artifactory, Curation checks it against a pre-indexed catalog of known risks -- without downloading the package first. Non-compliant packages are blocked and never stored.
How It Works
Developer request → Artifactory Remote Repo → Curation Check → Allow/Block → Cache or Reject
- Developer requests a package (e.g.,
npm install [email protected]) - Artifactory routes the request through its remote repository
- Curation evaluates the package against active policies using its pre-indexed catalog
- If compliant: package is downloaded, cached, and served
- If non-compliant: request is blocked, package never enters Artifactory
Policy Types
| Policy Type | What it blocks |
|---|---|
| Malicious Package | Packages flagged as malicious by JFrog threat research |
| Critical Vulnerability | Packages with CVEs above a severity threshold (CVSS) |
| Viral License | Packages with GPL, AGPL, or other copyleft licenses |
| Outdated Package | Packages past end-of-life or with much newer versions available |
| Unofficial Docker Image | Docker images that are not official or verified |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 165 lines · 58 tokens per session scan A be3ee16b886c
JFrog Curation is a skill published in the GitHub repository jfrog/ai-agent-examples (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,581 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…