Codex with ChatGPT Planning Loop
XiaoDuoYa/codex-with-chatgpt
Uses ChatGPT in the browser as the planning and review brain for a Codex session, with Codex keeping all execution and ChatGPT reading the workspace through a bridge.
Teaches Hermes to monitor and steer long-running sandboxed.sh missions: spot where a model is stuck, switch backends or models between turns, and send targeted hints.
Install Hermes Mission Control
$ npx skills add Th0rgal/sandboxed.sh --skill hermes-mission-control -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Th0rgal/sandboxed.sh hermes-mission-control --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Th0rgal/sandboxed.sh.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/hermes-mission-control .claude/skills/hermes-mission-control && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "hermes-mission-control" agent skill from https://github.com/Th0rgal/sandboxed.sh/tree/master/skills/hermes-mission-control into .claude/skills/hermes-mission-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hermes-mission-control", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Th0rgal/sandboxed.sh/tree/master/skills/hermes-mission-controlType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Th0rgal/sandboxed.sh --skill hermes-mission-control -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Th0rgal/sandboxed.sh hermes-mission-control --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Th0rgal/sandboxed.sh.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/hermes-mission-control .agents/skills/hermes-mission-control && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "hermes-mission-control" agent skill from https://github.com/Th0rgal/sandboxed.sh/tree/master/skills/hermes-mission-control into .agents/skills/hermes-mission-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hermes-mission-control", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Th0rgal/sandboxed.sh --skill hermes-mission-control -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Th0rgal/sandboxed.sh hermes-mission-control --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Th0rgal/sandboxed.sh.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/hermes-mission-control .cursor/skills/hermes-mission-control && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "hermes-mission-control" agent skill from https://github.com/Th0rgal/sandboxed.sh/tree/master/skills/hermes-mission-control into .cursor/skills/hermes-mission-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hermes-mission-control", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Th0rgal/sandboxed.sh.git --path skills/hermes-mission-control--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Th0rgal/sandboxed.sh --skill hermes-mission-control -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Th0rgal/sandboxed.sh hermes-mission-control --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Th0rgal/sandboxed.sh.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/hermes-mission-control .gemini/skills/hermes-mission-control && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "hermes-mission-control" agent skill from https://github.com/Th0rgal/sandboxed.sh/tree/master/skills/hermes-mission-control into .gemini/skills/hermes-mission-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hermes-mission-control", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Th0rgal/sandboxed.sh hermes-mission-controlInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Th0rgal/sandboxed.sh --skill hermes-mission-control -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Th0rgal/sandboxed.sh.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/hermes-mission-control .github/skills/hermes-mission-control && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "hermes-mission-control" agent skill from https://github.com/Th0rgal/sandboxed.sh/tree/master/skills/hermes-mission-control into .github/skills/hermes-mission-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hermes-mission-control", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Th0rgal/sandboxed.sh --skill hermes-mission-control -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Th0rgal/sandboxed.sh hermes-mission-control --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Th0rgal/sandboxed.sh.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/hermes-mission-control .opencode/skills/hermes-mission-control && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "hermes-mission-control" agent skill from https://github.com/Th0rgal/sandboxed.sh/tree/master/skills/hermes-mission-control into .opencode/skills/hermes-mission-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hermes-mission-control", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
hermes-mission-control- GitHub stars
- 516
- Token cost
- ~8.6k tokens
- SKILL.md length
- 4,536 words
- Files
- 1
- Skills in repo
- 9
- Repo updated
- First seen
- Licence
- None found
At a glance
Teaches Hermes to monitor and steer long-running sandboxed.sh missions: spot where a model is stuck, switch backends or models between turns, and send targeted hints.
- Works in 3 steps: get_mission_health(mission_id) — always… → If health flags a problem you don't… → Act (see playbook). Then leave it alone…
- Babysitting a sandboxed.sh mission that runs for days or weeks
- SKILL.md covers How sandboxed.sh works (the…, Continue existing work without…, The monitoring loop and Intervention playbook, plus 11 more sections
- Needs CHATGPT_PASSWORD
What it does
Here the agent is a supervisor, not a coder, for sandboxed.sh missions: long-lived AI coding runs inside a workspace, executed by a backend such as `claudecode`, `codex`, `opencode`, `antigravity` or `grok`. It watches a mission, notices when it is struggling and intervenes so progress continues, preferring durable callbacks and scheduled wakeups over polling. Everything goes through the `sandboxed_assistant` MCP tools, and it never touches the host directly.
The skill explains the mission model: turns, statuses running from `pending` and `active` through `awaiting_user` to `completed`, or `interrupted`, `blocked`, `failed` and `not_feasible`, a watchdog that marks a mission interrupted after about 15 minutes of silence with no live tool, and the rule that backend, model, effort and agent settings change only between turns. It also covers boss and worker missions, a read-only `chatgpt_ui` consultation backend, and continuing work with `continue_identity`, which needs the stored project, track and PR copied from `get_mission`. The excerpt is truncated.
When your agent uses it
- Babysitting a sandboxed.sh mission that runs for days or weeks
- Diagnosing why a mission has stalled or keeps stopping early
- Switching a mission's backend or model between turns
- Resuming or nudging a mission with a targeted hint
Example prompts
- “Check on my sandboxed.sh mission and tell me whether it's stuck.”
- “The mission stalled on the same test failure, so switch it to another backend and keep it going.”
- “Resume the mission and send it a hint about the failing migration.”
Requirements
- Access to a sandboxed.sh deployment through the `sandboxed_assistant` MCP tools
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- get_mission_health(mission_id) — always start here. It returns live run
- If health flags a problem you don't understand, get_mission_diagnostics —
- Act (see playbook). Then leave it alone until the next check-in. Do not
What it can do on your machine
Read from SKILL.md and the folder at commit 6b0d233. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash and json).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
CHATGPT_PASSWORD
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Hermes Mission Control loads about 8.6k tokens when it runs. Until then it costs about 99 tokens; SKILL.md has 4,536 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 4,536 words (~8,626 tokens).
“You manage sandboxed.sh missions on the operator's behalf. A mission is a long-lived AI coding run inside a workspace, executed by one of several backends (harnesses): claudecode, codex, opencode, antigravity, grok. The separate chatgpt_ui backend is a read-only expert-consultation lane…”
- name
- hermes-mission-control
- metadata.policy
- chatgpt-ui-pool
- metadata.policy_version
- 1.4.0
- version
- 1.14.0
Files
Just SKILL.md in skills/hermes-mission-control of Th0rgal/sandboxed.sh.
Open the folder on GitHubat commit 6b0d233
Compare with similar skills
Hermes Mission Control next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Hermes Mission Control this skillTh0rgal/sandboxed.sh | 516 | — | ~8.6k | Automated safety check: Pass | None | |
| Codex with ChatGPT Planning LoopXiaoDuoYa/codex-with-chatgpt | 7.2k | — | ~11k | Automated safety check: Notes | MIT | |
| agtx One-Shot Project Runnerfynnfluegge/agtx | 1.7k | — | ~3.8k | Automated safety check: Pass | Apache-2.0 | |
| Puppetmaster Agent Orchestrationprofessorpalmer/Puppetmaster | 467 | — | ~3.2k | Automated safety check: Pass | MIT | |
| Agent Deck Sessionsartwist-polyakov/polyakov-claude-skills | 208 | — | ~965 | Automated safety check: Pass | MIT | |
| Ruflo Multi-Agent Orchestrationruvnet/ruflo | 74k | 1 repos | ~975 | Automated safety check: Pass | MIT |
Similar skills
agtx One-Shot Project Runner
fynnfluegge/agtx
Runs a whole project unattended on an agtx kanban board, decomposing the goal, starting tasks, unblocking workers and merging each result.
Puppetmaster Agent Orchestration
professorpalmer/Puppetmaster
Operates and supervises Puppetmaster, a multi-agent orchestrator, through its MCP tools or CLI, picking the right verb for edits, reviews, audits and long-running jobs.
Agent Deck Sessions
artwist-polyakov/polyakov-claude-skills
Launches, monitors and collects results from child AI agent sessions with the agent-deck terminal session manager.
Ruflo Multi-Agent Orchestration
ruvnet/ruflo
Sets up and drives Ruflo, an npm-installed orchestration layer for multi-agent swarms, persistent memory, routing, hooks and its MCP tool catalog.
Marm Init
Lyellr88/marm-memory
Guided MARM MCP setup. An agent skill from Lyellr88/marm-memory.
More from Th0rgal/sandboxed.sh
All 9 skills in this repoSandboxed.sh Library Management
Th0rgal/sandboxed.sh
Reads and updates the Sandboxed.sh Library, a git-backed store of skills, agents, commands, tools, rules and MCP servers, through its library tools.
Sandboxed.sh Missions
Th0rgal/sandboxed.sh
Delegates multi-step coding or research tasks to isolated sandboxed.sh container missions through its MCP tools, each with a chosen workspace, agent profile and prompt.
Orchestrator Executor
Th0rgal/sandboxed.sh
Has the agent do the implementation itself and consult one persistent, stronger advisor through ask_worker only when it reaches a dead end.
Orchestrator Worker
Th0rgal/sandboxed.sh
Sets the rules for a worker agent spawned by a boss mission: stay in scope, verify before finishing, report blockers quickly and end with a clear status.
Orchestrator Advisor
Th0rgal/sandboxed.sh
Acts as a persistent read-only advisor that maps the repository once, then answers a cheaper executor agent's questions concisely across a long session.
Orchestrator Boss
Th0rgal/sandboxed.sh
Boss skill for parallel worker orchestration. An agent skill from Th0rgal/sandboxed.sh.
Related
Works with
Categories
Questions about Hermes Mission Control
What does Hermes Mission Control do?
Teaches Hermes to monitor and steer long-running sandboxed.sh missions: spot where a model is stuck, switch backends or models between turns, and send targeted hints. sh missions: long-lived AI coding runs inside a workspace, executed by a backend such as `claudecode`, `codex`, `opencode`, `antigravity` or `grok`. It watches a mission, notices when it is struggling and intervenes so progress continues, preferring durable callbacks and scheduled wakeups over polling.
When should I use Hermes Mission Control?
Hermes Mission Control fits situations like: babysitting a sandboxed.sh mission that runs for days or weeks; diagnosing why a mission has stalled or keeps stopping early; switching a mission's backend or model between turns; resuming or nudging a mission with a targeted hint.
How do I install Hermes Mission Control in Claude Code?
Run `npx skills add Th0rgal/sandboxed.sh --skill hermes-mission-control -a claude-code`. Or copy the skill folder (skills/hermes-mission-control in Th0rgal/sandboxed.sh) into .claude/skills/hermes-mission-control in your project. Claude Code loads it when a task matches its description.
How do I install Hermes Mission Control in Codex?
Run `npx skills add Th0rgal/sandboxed.sh --skill hermes-mission-control -a codex`. Or copy the skill folder (skills/hermes-mission-control in Th0rgal/sandboxed.sh) into .agents/skills/hermes-mission-control in your project. Codex loads it when a task matches its description.
Can I use Hermes Mission Control in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Th0rgal/sandboxed.sh --skill hermes-mission-control -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hermes-mission-control, .gemini/skills/hermes-mission-control, .github/skills/hermes-mission-control and .opencode/skills/hermes-mission-control in your project.
What does Hermes Mission Control need to run?
Going by SKILL.md and its folder, Hermes Mission Control needs credentials named CHATGPT_PASSWORD. Our summary lists: Access to a sandboxed.sh deployment through the `sandboxed_assistant` MCP tools.
Does Hermes Mission Control access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Hermes Mission Control safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Hermes Mission Control use?
No licence was found for Hermes Mission Control or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Hermes Mission Control use?
About 8.6k tokens (SKILL.md is roughly 35k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Hermes Mission Control?
Skills that share tags, products or a category with Hermes Mission Control: Codex with ChatGPT Planning Loop (XiaoDuoYa/codex-with-chatgpt, 7.2k stars), agtx One-Shot Project Runner (fynnfluegge/agtx, 1.7k stars), Puppetmaster Agent Orchestration (professorpalmer/Puppetmaster, 467 stars) and Agent Deck Sessions (artwist-polyakov/polyakov-claude-skills, 208 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Hermes Mission Control?
Th0rgal (a GitHub user) maintains it in Th0rgal/sandboxed.sh, which has 516 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 9, 2026.
Source: Th0rgal/sandboxed.sh on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.