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 agentmods add skills/z80dev/lemon/runtime-remshnpx skills add z80dev/lemon --skill runtime-remshgit clone --depth 1 https://github.com/z80dev/lemonWhat 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 | $0.00045 | $0.00821 |
| Opus 5 | $0.00023 | $0.00411 |
| Sonnet 5 | $0.00009 | $0.00164 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
runtime-remsh scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
runtime-remsh
Use this skill when the user asks to connect to a running Lemon instance, recompile changed Elixir code without restarting, or run Elixir inside the live runtime.
Trigger
Use this skill for requests like:
- "connect to the running gateway"
- "attach to lemon and run recompile()"
- "execute this Elixir in the live runtime"
- "run rpc-eval against the node"
Preconditions
- The target process must be started as a distributed node (
--snameor--name) with a cookie. - The attaching shell must use the same naming mode and same cookie.
- For
./bin/lemon-gateway, do not use--no-distribution.
Quickstart (local gateway)
Start gateway (terminal 1):
./bin/lemon-gateway
Attach from another terminal (short-name default):
iex --sname lemon_attach --cookie lemon_gateway_dev_cookie --remsh "lemon_gateway@$(hostname -s)"
If gateway was started with explicit settings, use those exact values:
./bin/lemon-gateway --sname lemon_gateway --cookie "change-me"
iex --sname lemon_attach --cookie "change-me" --remsh "lemon_gateway@$(hostname -s)"
For long-name mode:
./bin/lemon-gateway --name [email protected] --cookie "change-me"
iex --name [email protected] --cookie "change-me" --remsh [email protected]
Tip: ./bin/lemon-gateway prints the exact Remote shell target to use.
Recompile changed code in the live runtime
Inside attached IEx:
recompile()
Useful follow-up checks:
node()
Application.started_applications() |> Enum.map(&elem(&1, 0))
If needed, force reload a module:
r(LemonGateway.Run)
Execute arbitrary Elixir code in the live runtime
Interactive (--remsh) examples:
LemonGateway.Config.get()
LemonGateway.Config.get(:default_engine)
Non-interactive one-off (--rpc-eval) example:
elixir --sname lemon_probe --cookie lemon_gateway_dev_cookie --rpc-eval "lemon_gateway@$(hostname -s)" "IO.inspect(LemonGateway.Config.get(:default_engine))"
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.
- 2d ago First seen · 118 lines · 45 tokens per session scan A f26d41f6f4f8
runtime-remsh is a skill published in the GitHub repository z80dev/lemon (129 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 821 once invoked, about $0.0002 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.
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…
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…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…