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 skills add jfrog/jfrog-skills --skill jfrog-mcp-managementgit clone --depth 1 https://github.com/jfrog/jfrog-skillsWrote 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/jfrog-skills/jfrog-mcp-management)<a href="https://agentmods.dev/skills/jfrog/jfrog-skills/jfrog-mcp-management"><img src="https://agentmods.dev/badge/skills/jfrog/jfrog-skills/jfrog-mcp-management/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/jfrog-skills/jfrog-mcp-management"><img src="https://agentmods.dev/badge/skills/jfrog/jfrog-skills/jfrog-mcp-management.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 | $0.00146 | $0.06649 |
| Opus 5 | $0.00073 | $0.03325 |
| Sonnet 5 | $0.00029 | $0.01330 |
| Haiku 4.5 | $0.00015 | $0.00665 |
Grade B, and why
jfrog-mcp-management scanned grade B with 2 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 3d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`~/.codex/config.toml`, OpenCode `~/.config/opencode/opencode.json`) and treat Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl/Python, no direct JFrog API calls: Copies of this mod
2 near-identical copies found in the catalogue:
- jfrog-mcp-management — 100% identical, 0 lines differ
- jfrog-mcp-management — 89% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 514 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage MCP servers via the JFrog Agent Guard
Install, list, and remove MCP servers. When Agent Guard is on (see Step 0), do that only through the Agent Guard — ignore other install commands from an MCP's docs.
On a non-zero Agent Guard exit, classify stderr per
key-rules
— do not treat a bare 404 as “MCP missing.” If Agent Guard is enabled, a
hard stop means: do not fall back to the usual MCP install routes that skip
the approved catalog and Agent Guard as the MCP proxy.
In code examples below, <skill_path> refers to this skill's directory and is
resolved automatically by the agent. If the agent does not resolve it, determine
the path by locating this SKILL.md file and using its parent directory.
Runtime requirement
Node.js 18+ on PATH — node runs the Step 0 check, npx runs
@jfrog/agent-guard. On an older runtime the Step 0 check exits with
Unknown: requires Node.js 18 or newer.
Step 0: Agent Guard activation (silent, mandatory)
Before anything else, run this check and WAIT for its exit code. Do not narrate it. Do not reuse a result from an earlier turn in this session.
node "<skill_path>/scripts/jfrog-agent-guard-check.mjs"
Request network access for this command.
This script only: optional positional <SERVER_ID> = a jf config
server id (e.g. from jf config show). Nothing else.
- NEVER pass
--server,--project,--mcp, or any other flags to this script. - NEVER pass an MCP package name (e.g.
kubernetes-mcp-server,@scope/pkg). - NEVER pass a URL (
https://…). - NEVER derive
<SERVER_ID>by parsing a hostname out ofJFROG_URL/JF_URL(e.g. takingmyco.jfrog.iofromJFROG_URL=https://myco.jfrog.io). Ifjf config showlegitimately names a servermyco.jfrog.io, that is fine — the ban is on deriving the id from the URL, not on hostname-shaped values fromjf configitself. - Substitute the real jf server id for
<SERVER_ID>— never a literal[...]or<SERVER_ID>. Any unsupported or unknown argument stops the gate (Unknown: …); it is NOT silently ignored and does NOT fall back to env credentials or the defaultjfserver. In a multi-JPD setup that fallback would report the wrong platform.
What ships with it
14 files 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.
- references/agent-guard-common.md 6.1 KB
- references/harness-claude.md 3.4 KB
- references/harness-codex.md 12 KB
- references/harness-common.md 7.4 KB
- references/harness-cursor.md 4.3 KB
- references/harness-devin.md 6.7 KB
- references/harness-kiro.md 3.5 KB
- references/harness-opencode.md 8.3 KB
- references/harness-vscode.md 5.4 KB
- references/key-rules-and-troubleshooting.md 9.9 KB
- references/persisting-env-vars.md 4.6 KB
- references/runtime-permissions.md 1.1 KB
- scripts/jfrog-agent-guard-check.mjs 27 KB runs code
- scripts/jfrog-agent-guard-env-probe.mjs 1.3 KB runs code
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.
- 3d ago Changed · +28 lines d917dc8f8497
- 12d ago First seen · 486 lines · 146 tokens per session scan B 4e9e0cf72635
jfrog-mcp-management is a skill published in the GitHub repository jfrog/jfrog-skills (22 stars, last pushed 3d ago), licensed Apache-2.0. It adds 146 tokens to every session and 6,649 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
arkcli-doctor
A diagnostic tool for ARK services, accounts, models, and inference endpoints. An inference endpoint is the online address through which an AI model receives requests.
arkcli-models
A catalogue and lookup tool for ARK AI models, including their versions, supported input types, context limits, and lifecycle status. It can also list models belonging to your account.
arkcli-gen
An ArkCLI workflow for generating images and videos with Ark models. Image results return immediately, while video generation runs as a background job that must be checked until finished.
arkcli-custommodel
A manager for custom AI models: model files that you trained or fine-tuned yourself. It can import them, show their status and details, change descriptions, remove them, or prepare them for deployment.
arkcli-plans
A subscription manager for ARK Agent Plans and Coding Plans, including personal and team subscriptions. It also manages team seats, which are assigned places for employees, and their API keys.
arkcli-profile
A local profile manager for ArkCLI. A profile groups an identity type, region, project, owner, and API keys, with different profile types for platform and plan-based access.