thurbox-cli

A command-line tool for creating and managing coding-agent sessions, tasks, messages, editors, settings, extensions, and plugins. It can run sessions locally or on remote hosts and organize lead and worker sessions.

In plain words
What is it for?
Use it to start sessions, attach repositories, create tasks, send messages, manage session hooks, and control agent-related configuration from scripts or a terminal.
Why use it?
It lets developers control agent work without opening the terminal user interface. Shared session storage and messaging make it easier to coordinate work across repositories and agents.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/thurbeen/thurbox/thurbox-cli
Any agent
npx skills add Thurbeen/thurbox --skill thurbox-cli
Clone the repo
git clone --depth 1 https://github.com/Thurbeen/thurbox

Made for: Claude Code, Codex.

Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,248 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00104 $0.06248
Opus 5 $0.00052 $0.03124
Sonnet 5 $0.00021 $0.01250
Haiku 4.5 $0.00010 $0.00625

Measured 2d ago against content hash 43d35ba69e4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

thurbox-cli 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.

.claude/skills/thurbox-cli/SKILL.md · 380 lines

How it starts

The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.

thurbox-cli, automations, tasks and messages

Working reference extracted from CLAUDE.md, which indexes it. The rationale behind these decisions is owned by the docs under docs/; a change that invalidates what this says updates it in the same PR.

thurbox-cli

A second binary (thurbox-cli) drives the same SQLite-backed, tmux-hosted sessions headlessly (no TUI). It shares the database with the TUI; changes appear via PRAGMA data_version polling.

cargo build --bin thurbox-cli
thurbox-cli session create --name demo --repo-path /path \
    --agent codex --worktree-branch feat/x
# Spawn on a remote host from hosts.toml (worktree + tmux live remotely):
thurbox-cli session create --name demo --repo-path /srv/repo \
    --host devbox --worktree-branch feat/x
# Spawn a worker under a lead session (parent must exist):
thurbox-cli session create --name worker --repo-path /path \
    --parent <lead-uuid>
# Multi-repo: each --add-repo gets its own worktree on --worktree-branch;
# --add-dir attaches a repo as-is (no branch). The agent launches in a
# symlink workspace gathering every repo. Works on `task create` too.
thurbox-cli session create --name demo --repo-path /a \
    --agent claude --worktree-branch feat/x \
    --add-repo /b@main --add-repo /c@master --add-dir /reference
thurbox-cli session list                       # human-readable table
thurbox-cli session list --json | jq           # machine output for scripts
thurbox-cli session list --parent <lead-uuid> --json | jq  # direct children only

Subcommands: session (create/list [--deleted]/get/delete/restore/restart [--if-missing]/send [--no-enter]/key/capture/focus/signal/doctor/sync/register — sync/register and the flags serve session sharing, ADR-24), automation (alias auto: create/list/show/edit/remove/run/runs/tick), task (alias todo: create/list/show/edit/remove/run), message (alias msg: send/inbox/prune — the inter-session mailbox queue; see below), editor (get/set the Ctrl+O editor command; editor mode <auto|terminal|gui> chooses how it launches — terminal editors get a real TTY via a tmux popup or TUI suspend, GUI editors spawn detached; see the Editor Integration section of docs/FEATURES.md), config (validate/show — strict-parses every config file / prints the effective resolved config; see docs/CONFIG.md), extension (alias ext: install/uninstall/reinstall/list/available/update/activate/ deactivate/status — manage opt-in extensions; see below), version (prints the running version; --check queries GitHub's latest release — gated on [features] version_check, on by default for 1.0), update (downloads, verifies, and replaces the installed binaries with the latest release within the current major — a new major is reported, never installed, because 2.x replaced the whole interface; --force bypasses the up-to-date/dev-build/major guards; gated on [features] auto_update, on by default for 1.0; the TUI also runs this silently on startup when the flag is on), notify (diagnose OS desktop notifications: prints the detected delivery backend and last error; --test fires a sample — see OS notifications below), perf (print the perf snapshot a running TUI publishes while THURBOX_PERF_LOG or its perf HUD is active — see docs/PERFORMANCE.md), plugin (v2 interface plugins without a TTY: dir reports the directory in force and which of the two rules chose it, new <name> writes a starter that already loads, check loads the interface the way thurbox does and exits non-zero on a failure — including on a pane that loaded but which no arrangement places, printing the layout.lua line to add — list is the same inventory the settings modal's Interface tab shows, and events lists every event a plugin may subscribe to with its payload, and install|sync|update|remove|available manage panes from a declarative spec — see docs/PLUGINS.md).

Read the full file on GitHub · 380 lines

Changes

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.

  1. 2d ago First seen · 380 lines · 0 tokens per session scan A 43d35ba69e4e

Subscribe to this mod's changes

thurbox-cli is a skill published in the GitHub repository Thurbeen/thurbox (57 stars, last pushed 2d ago), licensed MIT. It adds 104 tokens to every session and 6,248 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens