Updated 1w ago
by Th0rgal
sandboxed.sh
Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.
515 GitHub stars (515)
+2 in 16 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | +1 |
| Oct 6 | +1 |
| Oct 7 | 0 |
- 9 skills (9 skills found in its SKILL.md files)
- 53 forks (53 forks)
- 1w ago last update (Last updated 1w ago)
Install
Skills CLI
npx skills add Th0rgal/sandboxed.sh
Asks which skills and agents to install. Just one: npx skills add Th0rgal/sandboxed.sh --skill controllers-policy — add -g for every project.
Claude Code
git clone https://github.com/Th0rgal/sandboxed.shcp -r "sandboxed.sh/skills/controllers-policy" ~/.claude/skills/
Copies the controllers-policy skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add Th0rgal/sandboxed.sh
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
controllers-policy
Autonomy contract and routing index for autonomous project controllers. Loaded every tick; carries the rules that must survive cron-prompt rewrites.
skills/controllers-policy/SKILL.md on GitHub (opens in a new tab) -
hermes-mission-control
How Hermes monitors and steers long-running sandboxed.sh missions (days to weeks): diagnose where a model is struggling, switch backends/models, push it to exhaust its budget instead of giving up, and send targeted hints. Trigger terms: mission, sandboxed.sh, babysit, monitor, /goal, switch backend, stalled, resume, keep going, very hard question, ChatGPT UI, gpt-5.6-pro.
skills/hermes-mission-control/SKILL.md on GitHub (opens in a new tab) -
orchestrator-advisor
Persistent read-only advisor mission. Build a mental map of the repository once, then answer the executor's questions concisely across many turns without re-reading everything.
skills/orchestrator-advisor/SKILL.md on GitHub (opens in a new tab) -
orchestrator-boss
Boss skill for parallel worker orchestration. Analyze, split, delegate by outcome, judge by acceptance criteria, integrate. Do not implement directly.
skills/orchestrator-boss/SKILL.md on GitHub (opens in a new tab) -
orchestrator-executor
Executor skill: do the work yourself, and consult a single persistent smart-model advisor via ask_worker when you hit a dead end.
skills/orchestrator-executor/SKILL.md on GitHub (opens in a new tab) -
orchestrator-worker
Worker skill for boss-spawned missions. Stay within scope, verify, and report blockers quickly.
skills/orchestrator-worker/SKILL.md on GitHub (opens in a new tab) -
project-manager
Steer sandboxed.sh projects, roadmaps, decisions from chat.
skills/project-manager/SKILL.md on GitHub (opens in a new tab) -
sandboxed-sh-missions
Delegate coding/automation tasks to sandboxed.sh missions via the mcp_sandboxed_assistant_* MCP. Each mission runs in an isolated container (workspace) with a chosen agent profile and a self-contained prompt. Use this skill whenever the user wants to 'launch a mission', 'sandboxed', 'spawn a worker', or delegate a multi-step coding/research task that should run in a clean environment.
skills/sandboxed-sh-missions/SKILL.md on GitHub (opens in a new tab) -
library-management
Manage the Sandboxed.sh library (skills, agents, commands, tools, rules, MCPs) via Library API tools. Trigger terms: library, skill, agent, command, tool, rule, MCP, save skill, create skill.
.opencode/skill/library-management/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod…
-
ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
-
awesome-claude-skillsby ComposioHQ A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
-
marketingskillsby coreyhaines31 Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.
-
CowAgentby zhayujie Open-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent,…
-
planning-with-filesby OthmanAdi Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and c…