local-codex

Engineering Community

Repo stars 0
Author updated Aug 24, 2026, 03:33 PM
Author repo claude-code-skills

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: Launch and manage OpenAI Codex CLI (local agent) as a non-interactive coding sub-agent. Use when the user wants to delegate codi…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “When to Use”, “Authentication (OAuth / ChatGPT Pro)”, “Codex CLI Path”, “Usage Patterns”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name local-codex directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “When to Use / Authentication (OAuth / ChatGPT Pro) / Codex CLI Path” before expanding.

Boundaries And Review

Dependencies: Prepare OpenAI API keys before running a full task.
Permissions: Declared permissions include read / write / shell-exec / env-read; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

Local Codex

Delegate coding tasks to the local OpenAI Codex CLI agent using your ChatGPT Pro subscription (OAuth, no API charges).

When to Use

User wants to generate, refactor, or review code via Codex
User wants to run codex exec for non-interactive tasks
User wants to use Codex's GPT-5.5 agent capabilities
User mentions "codex", "run codex", "delegate to codex"

Authentication (OAuth / ChatGPT Pro)

CRITICAL: This skill uses OAuth authentication from ~/.codex/auth.json (ChatGPT Pro flat-rate subscription). Do NOT set OPENAI_API_KEY or pass API keys — that would switch to pay-per-use billing.

Codex desktop app and CLI share the same auth cache
If auth fails, run codex login in terminal (browser OAuth flow)
For auth issues, see references/oauth-guide.md

Codex CLI Path

The skill auto-detects Codex CLI in this order:

/Applications/Codex.app/Contents/Resources/codex (desktop app)
/usr/local/bin/codex (npm global)
/opt/homebrew/bin/codex (Homebrew)
~/.npm-global/bin/codex
which codex fallback

Usage Patterns

1. Basic exec (single task)

python3 scripts/codex_wrapper.py exec "<prompt>" [<workdir>] [<model>] [<sandbox>] [<timeout>]

Example:

python3 scripts/codex_wrapper.py exec \
  "Write a Python function to calculate fibonacci" \
  /tmp \
  gpt-5.5 \
  workspace-write \
  300

2. Code review

python3 scripts/codex_wrapper.py review [<workdir>] [<model>] [uncommitted:true] [<timeout>]

Example:

python3 scripts/codex_wrapper.py review \
  /path/to/repo \
  gpt-5.5 \
  true \
  300

3. Check status

python3 scripts/codex_wrapper.py status

Output Format

The wrapper returns JSON with:

success: bool
exit_code: int
elapsed_seconds: float
stdout: raw output
stderr: error stream (truncated)
parsed_jsonl: parsed JSONL events (if --json)
final_message: extracted assistant text (if available)

Parameters

Parameter	Default	Options
model	`gpt-5.5`	`gpt-5.5`, `gpt-5.5-pro`, `o4-mini`, etc.
sandbox	`workspace-write`	`read-only`, `workspace-write`, `danger-full-access`
timeout	300	seconds (increase for large tasks)
json_output	true	always true (wrapper parses JSONL)

Safety Notes

sandbox=read-only for analysis/review tasks (no file writes)
sandbox=workspace-write for code generation (writes to working dir)
sandbox=danger-full-access only when explicitly needed (full system access)
Always use --skip-git-repo-check when running outside git repos
Use --ephemeral for one-off tasks (no session persistence)

Session Management

For multi-step tasks, Codex supports session resume:

# First step
codex exec --ephemeral "Step 1..."
# Later
codex exec resume --last "Step 2..."

The wrapper currently runs single-shot exec. For multi-step workflows, use raw codex exec commands.

Limitations

Desktop app must be running for OAuth token refresh (or token must be fresh)
codex doctor is buggy in current version (alpha), avoid using
Environment variables are NOT inherited into Codex's sandbox; pass via config or prompt
Large file operations may need increased timeout

Fluxly profile Author and license come from source; runtime, permissions, and network are Fluxly detections or estimates

Fluxly category: Engineering
Author-declared agents: No explicit declaration found; this is not inferred or tested compatibility
Static check: 88 / 100 · heuristic scan, not runtime safety proof
Author / version / license: @daymade · no license declared
Fluxly token estimate: Lean
Fluxly setup estimate: Guided setup
External API key: Required · OpenAI
Detected OS requirements: macOS · Linux · Windows
Runtime requirements: Python
Detected file/system behavior: Read-only
Write / modify
Shell exec
Env read
Detected network behavior: External requests
Install commands: None (reference only)

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview local-codex.preview

The current SKILL.md does not define a fixed output example.

SKILL.md SKILL.md

# Local Codex

Delegate coding tasks to the local OpenAI Codex CLI agent using your ChatGPT Pro subscription (OAuth, no API charges).

## When to Use

- User wants to generate, refactor, or review code via Codex
- User wants to run `codex exec` for non-interactive tasks
- User wants to use Codex's GPT-5.5 agent capabilities
- User mentions "codex", "run codex", "delegate to codex"

## Authentication (OAuth / ChatGPT Pro)

**CRITICAL**: This skill uses OAuth authentication from `~/.codex/auth.json` (ChatGPT Pro flat-rate subscription). **Do NOT set `OPENAI_API_KEY` or pass API keys** — that would switch to pay-per-use billing.

- Codex desktop app and CLI share the same auth cache
- If auth fails, run `codex login` in terminal (browser OAuth flow)
- For auth issues, see [references/oauth-guide.md](references/oauth-guide.md)

## Codex CLI Path

The skill auto-detects Codex CLI in this order:
1. `/Applications/Codex.app/Contents/Resources/codex` (desktop app)
2. `/usr/local/bin/codex` (npm global)
3. `/opt/homebrew/bin/codex` (Homebrew)
4. `~/.npm-global/bin/codex`
5. `which codex` fallback

## Usage Patterns

### 1. Basic exec (single task)

```bash
python3 scripts/codex_wrapper.py exec "<prompt>" [<workdir>] [<model>] [<sandbox>] [<timeout>]
```

Example:
```bash
python3 scripts/codex_wrapper.py exec \
  "Write a Python function to calculate fibonacci" \
  /tmp \
  gpt-5.5 \
  workspace-write \
  300
```

### 2. Code review

```bash
python3 scripts/codex_wrapper.py review [<workdir>] [<model>] [uncommitted:true] [<timeout>]
```

Example:
```bash
python3 scripts/codex_wrapper.py review \
  /path/to/repo \
  gpt-5.5 \
  true \
  300
```

### 3. Check status

```bash
python3 scripts/codex_wrapper.py status
```

## Output Format

The wrapper returns JSON with:

…

Evidence boundary and execution chain

Author text anchors workflow facts; Fluxly only indexes current sections, terms, files, and commands.

sections -> When to Use → Authentication (OAuth / ChatGPT Pro) → Codex CLI Path → Usage Patterns → 1. Basic exec (single task) → 2. Code review
terms    -> CRITICAL · Do NOT set OPENAIAPIKEY or pass API keys · Delegate coding tasks to the local OpenAI Codex CLI agent using your ChatGPT Pro subscription (OAuth, no API charges). · CRITICAL: This skill uses OAuth authentication from ~/.codex/auth.json (ChatGPT Pro flat-rate subscription). · The skill auto-detects Codex CLI in this order: 1. · | Parameter | Default | Options | |-----------|---------|---------| | model | gpt-5.5 | gpt-5.5, gpt-5.5-pro, o4-mini, etc. · The wrapper currently runs single-shot exec.
files/cmd -> codex exec · ~/.codex/auth.json · OPENAIAPIKEY · codex login · /Applications/Codex.app/Contents/Resources/codex · /usr/local/bin/codex · /opt/homebrew/bin/codex · ~/.npm-global/bin/codex
body sha256 -> 00efa63f9822