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 jolliai/jolliai --skill remote-rungit clone --depth 1 https://github.com/jolliai/jolliaiWrote 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/jolliai/jolliai/remote-run)<a href="https://agentmods.dev/skills/jolliai/jolliai/remote-run"><img src="https://agentmods.dev/badge/skills/jolliai/jolliai/remote-run/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/jolliai/jolliai/remote-run"><img src="https://agentmods.dev/badge/skills/jolliai/jolliai/remote-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00079 | $0.02252 |
| Opus 5 | $0.00039 | $0.01126 |
| Sonnet 5 | $0.00016 | $0.00450 |
| Haiku 4.5 | $0.00008 | $0.00225 |
Grade A, and why
remote-run scanned grade A with 0 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 12d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- jolli-remote-run — 91% identical, 14 lines differ
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jolli Remote Run
Run a Jolli workflow remotely: the Jolli backend executes the workflow server-side (it spends Jolli LLM budget, unlike a local run), and this recipe triggers the run, monitors it to a terminal state, and reports what it produced — the still-active article URLs, the pull-request URL when the destination is git-backed, and the workflow/run deep-links — then offers to open any of them.
Drive the steps below in order. Prefer the Jolli MCP tools for the run lifecycle —
the run tools (run_remote_workflow, cancel_remote_workflow) have no CLI
mirror — and shell the jolli CLI (via the run-cli entry script the sibling
skills also use) only for the deterministic monitor and the browser-open helper.
Every URL is read verbatim off the run report — never construct, guess, or look one up. A link that is not in the report was withheld on purpose (for example, a private Jolli-managed destination omits the PR link but keeps the article URLs); treat its absence as normal, never an error.
Shell prerequisite
This block requires a POSIX bash shell. On Linux/macOS the system bash works.
On Windows, use Git Bash (the bash bundled with Git for Windows). Other
Windows "bash" options — C:\Windows\System32\bash.exe, the WindowsApps
alias, or any WSL bash — see a separate Linux home directory and will not
find the Jolli entry script that lives under %USERPROFILE%.
If Git Bash is not available on Windows, STOP and tell the user: "Jolli skill needs Git Bash on Windows. Install Git for Windows from https://git-scm.com/download/win and retry."
Do NOT fall back to npm run, npx, node directly, PowerShell-native
commands, WSL bash, or any workspace-local script — those bypass the
security recipe and the dist resolver and will not produce valid output.
Step 1 — identify the workflow to run
Determine which workflow the user wants to run and keep its numeric id.
- If the
list_workflowstool is registered this session (on Claude Codemcp__jollimemory__list_workflows), call it to list the available workflows and present them to the user byname(use your host's interactive single-select tool if it has one — e.g. AskUserQuestion on Claude Code — otherwise list them as text). Keep the chosen workflow'sid. - Otherwise, ask the user which workflow to run and get its numeric
id.
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.
- 12d ago First seen · 175 lines · 79 tokens per session scan A 8f63cddc3f68
remote-run is a skill published in the GitHub repository jolliai/jolliai (141 stars, last pushed yesterday), licensed Apache-2.0. It adds 79 tokens to every session and 2,252 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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…
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…