getkimchi/kimchi is a terminal-based coding agent that helps with software development through Kimchi’s language-model infrastructure. It can run tasks with one selected model or coordinate multiple models, with model roles chosen by its orchestration system.
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 getkimchi/kimchi --skill kimchi-tmuxgit clone --depth 1 https://github.com/getkimchi/kimchiWrote 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/getkimchi/kimchi/kimchi-tmux)<a href="https://agentmods.dev/skills/getkimchi/kimchi/kimchi-tmux"><img src="https://agentmods.dev/badge/skills/getkimchi/kimchi/kimchi-tmux/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/getkimchi/kimchi/kimchi-tmux"><img src="https://agentmods.dev/badge/skills/getkimchi/kimchi/kimchi-tmux.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 | $0.00014 | $0.00741 |
| Opus 5 | $0.00007 | $0.00370 |
| Sonnet 5 | $0.00003 | $0.00148 |
| Haiku 4.5 | $0.00001 | $0.00074 |
Grade A, and why
kimchi-tmux 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 yesterday.
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.
What it actually says
Kimchi tmux control
Use the bundled controller script to start, inspect, drive, stop, and resume a real Kimchi session. It needs Node.js 22+, tmux, and an existing provider login. Invoke the script by its absolute path, resolved relative to this skill's location; skills may be loaded from a temporary copy.
The controller uses kimchi on PATH. To test a development checkout, build it with pnpm run build:binary and set KIMCHI_BINARY=/absolute/checkout/dist/bin/kimchi before start. The run saves that executable path for resume. No feature resource is required unless testing that feature.
node /absolute/skill/scripts/harness-live.mjs start <model> [provider]
node /absolute/skill/scripts/harness-live.mjs status <run-dir>
node /absolute/skill/scripts/harness-live.mjs type <run-dir> '/model'
node /absolute/skill/scripts/harness-live.mjs key <run-dir> Enter
node /absolute/skill/scripts/harness-live.mjs send <run-dir> '<prompt or /command>'
node /absolute/skill/scripts/harness-live.mjs send <run-dir> - < prompt.txt
node /absolute/skill/scripts/harness-live.mjs stop <run-dir>
node /absolute/skill/scripts/harness-live.mjs resume <run-dir>
Use the model the user requested; the provider defaults to kimchi-dev. Record the printed run directory. Each run gets a temporary Git workdir and starts in Plan mode, using existing settings/auth. Live model calls consume inference credits.
Inspect status until the editor is ready before injecting input, then between actions. start returning is not a readiness guarantee. Serialize controller calls for each run. status captures the original harness pane even if another pane/window becomes active, and prints the latest root session path. Its header describes the initial model; read the pane for the current model. Verify visible output and actual saved state rather than relying on an agent's claim.
type inserts one line without Enter and also fills menu search fields. send uses bracketed paste and Enter; use stdin (-) for multiline or large prompts. /model opens the model menu; C-p cycles models. Navigate with Up/Down, select with Enter, dismiss with Escape. Run --help for the supported keys, including Tab, Shift+Tab (BTab), Space, Backspace (BSpace), and PageUp/PageDown (PPage/NPage). C-c interrupts streaming but only denies the current request inside a permission dialog.
stop kills only the named tmux session and retains artifacts. resume chooses the latest root session, ignores evaluator children, and lets Kimchi restore its saved model. It requires a persisted session: an untouched editor may have nothing to resume. It does not restore an in-flight stream or open menu.
An agent driving the controller needs Default/Auto mode because Plan mode rejects launch; the child can remain in Plan mode. Approve scoped controller calls without disabling permission checks. A temporary workdir is not a security sandbox: keep prompts scoped there and forbid project/settings changes during read-only checks. For isolated checks, use a dedicated HOME and tmux server, keeping the same TMUX_TMPDIR for every call. Stop only sessions you created and remove temporary credentials after checking artifacts.
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.
- yesterday First seen · 32 lines · 14 tokens per session scan A 26d7405e40ba
kimchi-tmux is a skill published in the GitHub repository getkimchi/kimchi (2,225 stars, last pushed today), licensed Apache-2.0. It adds 14 tokens to every session and 741 once invoked, about $0.0001 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 2026-09-12.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.