Chalk Labs
Need help deploying Codex?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/avatar-arts-codex
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/codex
What's inside
- Skill name
Codex- Description
- Delegate coding to Codex CLI (features, PRs).
- License
- MIT
- Instructions
- 734 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: only lowercase letters, digits and single hyphens allowed
- name: "Codex" does not match folder "claude-code"
- body: 734 lines (spec recommends under 500)
Files (1)
- SKILL.md
SKILL.md (first lines)
# Codex — Hermes Orchestration Guide Delegate coding tasks to [Codex](https://code.Codex.com/docs/en/cli-reference) (Anthropic's autonomous coding agent CLI) via the Hermes terminal. Codex v2.x can read files, write code, run shell commands, spawn subagents, and manage git workflows autonomously. ## Prerequisites - **Install:** `npm install -g @anthropic-ai/Codex` - **Auth:** run `Codex` once to log in (browser OAuth for Pro/Max, or set `ANTHROPIC_API_KEY`) - **Console auth:** `Codex auth login --console` for API key billing - **SSO auth:** `Codex auth login --sso` for Enterprise - **Check status:** `Codex auth status` (JSON) or `Codex auth status --text` (human-readable) - **Health check:** `Codex doctor` — checks auto-updater and installation health - **Version check:** `Codex --version` (requires v2.x+) - **Update:** `Codex update` or `Codex upgrade` ## Two Orchestration Modes Hermes interacts with Codex in two fundamentally different ways. Choose based on the task. ### Mode 1: Print Mode (`-p`) — Non-Interactive (PREFERRED for most tasks) Print mode runs a one-shot task, returns the result, and exits. No PTY needed. No interactive prompts. This is the cleanest integration path. ``` terminal(command="Codex -p 'Add error handling to all API calls in src/' --allowedTools 'Read,Edit' --max-turns 10", workdir="/path/to/project", timeout=120) ``` **When to use print mode:** - One-shot coding tasks (fix a bug, add a feature, refactor) - CI/CD automation and scripting - Structured data extraction with `--json-schema` - Piped input processing (`cat file | Codex -p "analyze this"`) - Any task where you don't need multi-turn conversation **Print mode skips ALL interactive dialogs** — no workspace trust prompt, no permission confirmations. This makes it ideal for automation. ### Mode 2: Interactive PTY via tmux — Multi-Turn Sessions Interactive mode gives you a full conversational REPL where you can send follow-up prompts, use slash commands, and watch Codex work in real time. **Requires tmux orchestration.** ``` # Start a tmux session terminal(command="tmux new-session -d -s Codex-work -x 140 -y 40") # Launch Codex inside it terminal(command="tmux send-keys -t Codex-work 'cd /path/to/project && Codex' Enter") # Wait for startup, then send your task # (after ~3-5 seconds for the welcome screen) terminal(command="sleep 5 && tmux send-keys -t Codex-work 'Refactor the auth module to use JWT tokens' Enter") # Monitor progress by capturing the pane terminal(command="sleep 15 && tmux capture-pane -t Codex-work -p -S -50") # Send follow-up tasks terminal(command="tmux send-keys -t Codex-work 'Now add unit tests for the new JWT code' Enter") # Exit when done terminal(command="tmux send-keys -t Codex-work '/exit' Enter") ``` **When to use interactive mode:** - Multi-turn iterative work (refactor → review → fix → test cycle) - Tasks requiring human-in-the-loop decisions - Exploratory coding sessions - When you need to use Codex's slash commands (`/compact`, `/review`, `/model`) ## PTY Dialog Handling (CRITICAL for Interactive Mode) Codex presents up to two confirmation dialogs on first launch. You MUST handle these via tmux send-keys: ### Dialog 1: Workspace Trust (first visit to a directory) ``` ❯ 1. Yes, I trust this folder ← DEFAULT (just press Enter) 2. No, exit ``` **Handling:** `tmux send-keys -t <session> Enter` — default selection is correct. ### Dialog 2: Bypass Permissions Warning (only with --dangerously-skip-permissions) ``` ❯ 1. No, exit ← DEFAULT (WRONG choice!) 2. Yes, I accept ``` **Handling:** Must navigate DOWN first, then Enter: ``` tmux send-keys -t <session> Down && sleep 0.3 && tmux send-keys -t <session> Enter ``` ### Robust Dialog Handling Pattern ``` # Launch with permissions bypass terminal(command="tmux send-keys -t Codex-work 'Codex --dangerously-skip-permissions \"your task\"' Enter") # Handle trust dialog (Enter for default "Yes") terminal(command="sleep 4 && tmux send-keys -t Codex-work Enter") # Handle permissions dialog (Down then Enter for "Yes, I accept") terminal(command="sleep 3 && tmux send-keys -t Codex-work Down && sleep 0.3 && tmux send-keys -t Codex-work Enter") # Now wait for Codex to work terminal(command="sleep 15 && tmux capture-pane -t Codex-work -p -S -60") ``` **Note:** After the first trust acceptance for a directory, the trust dialog won't appear again. Only the permissions dialog recurs each time you use `--dangerously-skip-permissions`. ## CLI Subcommands | Subcommand | Purpose | |------------|---------| | `Codex` | Start interactive REPL | | `Codex "query"` | Start REPL with initial prompt | | `Codex -p "query"` | Print mode (non-interactive, exits when done) | | `cat file \| Codex -p "query"` | Pipe content as stdin context | | `Codex -c` | Continue the most recent conversation in this directory | | `Codex -r "id"` | Resume a specific session by ID or name | | `Codex auth login` | Sign in (add `--console` for API billing, `--sso` for Enterprise) | | `Codex auth status` | Check login status (returns JSON; `--text` for human-readable) | | `Codex mcp add <name> -- <cmd>` | Add an MCP server | | `Codex mcp list` | List configured MCP servers |
From AvaTar-ArTs/.Agent-skills, MIT.
More from AvaTar-ArTs/.Agent-skills
- 0.438score
ecosystem-layering
AvaTar-ArTs
Use when managing multiple AI coding agents (Codex, Cursor, Codex, Cline, Copilot, Gemini CLI, etc.) that share a home directory — to prevent…
SkillCFreshness: CClaude Code +9 - 0.435score
agmsg
AvaTar-ArTs
Cross-agent messaging via SQLite.
SkillCFreshness: CClaude Code +9 - 0.431score
agent-creation-guidance
AvaTar-ArTs
Guides the process of designing and creating autonomous agents, detailing structure, system prompts, triggering conditions, and development best practices.
SkillCFreshness: CClaude Code +9 - 0.430score
automation-recommender
AvaTar-ArTs
Analyze a codebase and recommend Codex automations (hooks, subagents, skills, plugins, MCP servers).
SkillCFreshness: CClaude Code +9 - 0.425score
deep-research
AvaTar-ArTs
Multi-agent research reports on any topic.
SkillCFreshness: CClaude Code +9 - 0.407score
agent-development
AvaTar-ArTs
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent…
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 10, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/AvaTar-ArTs/.Agent-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from AvaTar-ArTs
- 0.488score
agent-workflow-catalog
AvaTar-ArTs
Use when routing complex work through ordered skills and agents.
SkillBFreshness: BClaude Code +9 - 0.481score
automation-offer-workbench
AvaTar-ArTs
Use when productizing automation into reviewable offers.
SkillBFreshness: BClaude Code +9 - 0.481score
plugin-creator
AvaTar-ArTs
Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, validated manifest defaults, and…
SkillBFreshness: BClaude Code +9 - 0.476score
automate
AvaTar-ArTs
Use this skill to create Codex Automations.
SkillBFreshness: BClaude Code +9 - 0.475score
apple
AvaTar-ArTs
Use when working with Apple ecosystem tools - Reminders, FindMy, Notes, iMessage, Computer Use.
SkillBFreshness: BClaude Code +9 - 0.474score
evoked-publishing
AvaTar-ArTs
Turn approved source records into traceable publication packages.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get Codex running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
Codex skill. Agent Mart. https://agentmart.dev/skills/avatar-arts-codex (last updated 2026-10-24)