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/claude-plugin --skill jfrog-mcp-managementgit clone --depth 1 https://github.com/jfrog/claude-pluginWrote 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/claude-plugin/jfrog-mcp-management)<a href="https://agentmods.dev/skills/jfrog/claude-plugin/jfrog-mcp-management"><img src="https://agentmods.dev/badge/skills/jfrog/claude-plugin/jfrog-mcp-management.svg" alt="Measured on agentmods" 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 | $0.06247 |
| Opus 5 | $0.00073 | $0.03123 |
| Sonnet 5 | $0.00029 | $0.01249 |
| Haiku 4.5 | $0.00015 | $0.00625 |
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 5d 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: This is a copy
89% identical to jfrog-mcp-management — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 486 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 on PATH — node runs the Step 0 check, npx runs @jfrog/agent-guard.
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 5.8 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 2.5 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 9.2 KB
- references/persisting-env-vars.md 4.6 KB
- references/runtime-permissions.md 1.1 KB
- scripts/jfrog-agent-guard-check.mjs 13 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.
- 5d ago Changed · +38 lines 4e9e0cf72635
- 7d ago First seen · 448 lines · 146 tokens per session scan B 5dba582ff315
jfrog-mcp-management is a skill published in the GitHub repository jfrog/claude-plugin (6 stars, last pushed today), licensed Apache-2.0. It adds 146 tokens to every session and 6,247 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). It is 89% identical to jfrog-mcp-management, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…