# Claude Code Cli

> Delegate work from Codex to the local Claude Code CLI with low-waste, current command patterns. Use when Codex needs to call `claude`, choose Claude Code model or effort settings, use `ultrathink` or `ultracode`, run print-mode JSON calls, resume or continue Claude sessions across turns, manage background Claude agents or workflows, cap spend with `--max-budget-usd`, restrict Claude tools, or com…

- **Type:** Skill
- **Install:** `agentstack add skill-michaelihc-claude-code-cli-codex-skill-claude-code-cli`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Michaelihc](https://agentstack.voostack.com/s/michaelihc)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Michaelihc](https://github.com/Michaelihc)
- **Source:** https://github.com/Michaelihc/claude-code-cli-codex-skill/tree/main/claude-code-cli

## Install

```sh
agentstack add skill-michaelihc-claude-code-cli-codex-skill-claude-code-cli
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Claude Code CLI

Updated as of June 25, 2026. Verified against Claude Code CLI 2.1.191 and the official Claude Code docs available that day.

## Workflow

1. Confirm the local CLI and auth path before spending tokens:

   ```powershell
   claude --version
   claude auth status --text
   ```

   If the machine relies on saved Claude subscription auth, avoid `--bare` unless `ANTHROPIC_API_KEY` or an `apiKeyHelper` is configured. `--safe-mode` keeps auth while disabling customizations for troubleshooting.

2. Prefer print mode for agent-to-agent calls:

   ```powershell
   claude -p --output-format json --model haiku --effort low --max-turns 1 --max-budget-usd 0.05 --tools "" --disallowedTools "mcp__*" --strict-mcp-config "Reply with exactly: ok"
   ```

   Use `--tools ""` for no built-in tools. MCP tools are separate; add `--disallowedTools "mcp__*"` or `--strict-mcp-config` when the call should not reach MCP servers.

3. Parse the JSON result instead of scraping text. Inspect:

   - `result` for the response text
   - `session_id` for follow-up calls
   - `subtype`, `is_error`, `errors`, and exit code for failure handling
   - `total_cost_usd` and `modelUsage` for cost/model auditing

4. Keep a session alive by preserving `session_id` and the working directory:

   ```powershell
   claude -p --output-format json --model sonnet --effort high --max-turns 5 --max-budget-usd 0.30 "Start the analysis."
   claude -p --resume  --output-format json --max-turns 5 --max-budget-usd 0.30 "Continue from the prior answer."
   ```

   Run resume commands from the same project directory where the print-mode session started. Do not pass `--no-session-persistence` if a future turn may need the session.

## Mode Selection

Use the smallest mode that can answer the question:

- **Cheap consult:** `--model haiku --effort low --max-turns 1 --tools ""` for short classification, wording, or sanity checks.
- **Coding opinion:** `--model sonnet --effort medium|high --max-turns 3-8` when Claude should inspect or reason about code.
- **Hard reasoning:** `--model opus --effort xhigh|max` only when the task justifies higher spend.
- **One-turn deeper reasoning:** include `ultrathink` in the prompt. It adds an in-context instruction and does not change the API effort level.
- **Workflow orchestration:** include `ultracode` in the prompt for one task, or set `--settings '{"ultracode":true}'` for a print-mode session that should let Claude plan dynamic workflows. `ultracode` is not accepted by `--effort`; it runs with `xhigh` effort plus workflow orchestration.
- **Interactive or long task:** use `--bg`, `claude agents --json`, `claude logs `, `claude attach `, and `claude stop ` when a background Claude session is more appropriate than blocking Codex.

## Budget Defaults

`--max-budget-usd` is a guardrail, not a cost planner. Too-low caps can fail after Claude Code startup/cache overhead, even for tiny prompts. Start with these ceilings and lower only after measuring this machine:

- `haiku` low, no tools, one turn: `0.05`
- `sonnet` medium/high, small code consult: `0.15-0.30`
- `opus` xhigh/max, hard consult: `0.50+`
- `ultracode`, background agents, or workflows: set an explicit task budget that the user would consider acceptable

When a cap is hit, treat the result as failed even if tokens were spent. Retry only after adjusting scope, model, effort, or budget.

## Recipes

Use the bundled wrapper when it helps avoid quoting mistakes:

```powershell
python claude-code-cli/scripts/claude_call.py --prompt "Reply with exactly: ok" --budget 0.05 --result-only
```

Read `references/cli-options.md` before using less common features: `--bare`, `--safe-mode`, `--continue`, `--fork-session`, `--bg`, `--json-schema`, `stream-json`, `ultracode`, `/deep-research`, `ultrareview`, or MCP/tool allowlists.

### Resumable Low-Cost Thread

```powershell
$first = claude -p --output-format json --model haiku --effort low --max-turns 1 --max-budget-usd 0.05 --tools "" --disallowedTools "mcp__*" --strict-mcp-config "Remember the token alpha and reply with ready."
$sid = ($first | ConvertFrom-Json).session_id
claude -p --resume $sid --output-format json --model haiku --effort low --max-turns 1 --max-budget-usd 0.05 --tools "" --disallowedTools "mcp__*" --strict-mcp-config "What token did I ask you to remember?"
```

### Hard One-Turn Review

```powershell
claude -p --output-format json --model opus --effort xhigh --max-turns 3 --max-budget-usd 0.50 --append-system-prompt "Be concise. Return risks first." "ultrathink: Review this design decision: ..."
```

### Print-Mode Ultracode

```powershell
claude -p --output-format json --model opus --max-turns 10 --max-budget-usd 2.00 --settings '{"ultracode":true}' "ultracode: audit this repository for auth bypasses and return the top findings."
```

Print mode and the Agent SDK do not show interactive workflow approval prompts; permission behavior follows configured rules. Add an allowlist only for commands the task truly needs.

## Accuracy Rules

- Prefer official docs and `claude --help` over community snippets when flags disagree.
- Read the actual `modelUsage` field because aliases such as `haiku`, `sonnet`, `opus`, `fable`, `best`, and `[1m]` can resolve differently by provider, plan, version, and settings.
- Do not pass secrets in prompts. Claude CLI auth may use saved account state even when `ANTHROPIC_API_KEY` is absent.
- Do not use `--dangerously-skip-permissions` from Codex unless the user explicitly asked for it and the workspace risk is understood.
- For pure advice calls, disable tools. For code-edit delegation, constrain tools and working directories deliberately.
- Re-check docs if the current date is after June 25, 2026 and the task depends on newly released Claude Code flags or model behavior.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Michaelihc](https://github.com/Michaelihc)
- **Source:** [Michaelihc/claude-code-cli-codex-skill](https://github.com/Michaelihc/claude-code-cli-codex-skill)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-michaelihc-claude-code-cli-codex-skill-claude-code-cli
- Seller: https://agentstack.voostack.com/s/michaelihc
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.