codex-coder · sno-ai, codex — Claude Code skill: routing coding tasks
The codex-coder Claude Code skill assigns coding work to a Shell, TypeScript, Python, or Rust specialist. It activates for Codex coding requests, language migrations, and tasks that change files in several languages.
Apache-2.0 ★ 869 updated 2026-11-16
npx skills add sno-ai/sno-station-skills --skill codex-coder -a claude-codeWhat codex-coder does
codex-coder picks a language specialist and hands over repository work, implementation, and verification. It weighs the requested destination, files to be changed, project manifests, and nearby tests; migrations are routed by their target language. When those signals leave the destination unclear, it asks one brief question.
For mixed-language work, the skill splits file ownership and settles a shared contract before implementation. Checks cover each language and the smallest cross-language integration case. Full test suites run only at the owner's explicit request. Shell and file read/write tools are required, along with the chosen language skill in the user's Codex skills directory; if that skill is missing, work follows the repository's conventions.
What it helps with
- route a
.shchange to a Shell specialist - choose TypeScript, Python, or Rust from project files
- split a cross-language change around a shared contract
- implement a migration in its destination language
Example prompts for the agent
- Write this script in Python with Codex
- Move this module to Rust and update its callers
- Implement this feature in TypeScript and Python with one shared data format
How to install codex-coder
1Skills CLI (Vercel)
npx skills add sno-ai/sno-station-skills --skill codex-coder -a claude-code2Manually: put the files in place
~/.claude/skills/codex/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/codex/
1Skills CLI (Vercel)
npx skills add sno-ai/sno-station-skills --skill codex-coder -a codex2Manually: put the files in place
.agents/skills/codex/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add sno-ai/sno-station-skills --skill codex-coder -a cursor2Manually: put the files in place
.cursor/skills/codex/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install sno-ai/sno-station-skills skills/M-build-and-rollout/codex-coder/overlay/codex2Manually: put the files in place
.github/skills/codex/SKILL.md1Skills CLI (Vercel)
npx skills add sno-ai/sno-station-skills --skill codex-coder -a gemini-cli2Platform CLI
gemini skills install https://github.com/sno-ai/sno-station-skills --path skills/M-build-and-rollout/codex-coder/overlay/codexManually: put the files in place
.devin/skills/codex/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add sno-ai/sno-station-skills --skill codex-coder -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about codex-coder
How do I install codex-coder in Claude Code?
Run npx skills add sno-ai/sno-station-skills --skill codex-coder -a claude-code. The skill file is at ~/.claude/skills/codex/SKILL.md.
What does codex-coder do?
It selects a specialist for Shell, TypeScript, Python, or Rust work, then delegates implementation and code checks to that skill.
What does codex-coder need to run?
It requires Shell and file read/write tools. The user-level skill for the selected language must also be installed.
Source text
SKILL.md · Apache-2.0
---
name: codex-coder
description: Route production coding tasks to the user-level Shell, TypeScript, Python, or Rust Codex workflow. Use for "codex-coder", "Codex write", "generate with Codex", language migrations, or mixed Shell/TypeScript/Python/Rust implementation when Codex should choose the correct language specialist automatically.
requires:
programs: []
harness:
- {slot: 4.shell, need: required}
- {slot: 4.file-read-write, need: required}
---
# Codex Coder Router
Carry the task's finite time budget into the coding assignment, including test time.
Require a duration estimate before each targeted test run; full evaluation, unit,
integration, or repository suites require the owner's explicit request, not dispatcher
approval. New security checks require the owner's specific approval; auxiliary checks
must not block the requested function or development work.
Act as a thin dispatcher. Select the language skill, then let that skill own repository discovery, prompting, implementation, verification, and refinement. Do not keep a second copy of language rules here.
## Codex runs with the sandbox off
Keep the owner's configured `sandbox_mode = "danger-full-access"`; do not override it
in a dispatch, config, flag, or profile. A connection or credential error does not identify
its cause. Inspect the effective configuration, actual endpoint, and error; repair the
observed cause within existing authority. Preserve valid results from unaffected tests.
## Route the Target Language
Use this precedence order:
1. The language or destination the user explicitly requested.
2. The files the task must create or change.
3. The repository's manifest, immediate callers, and nearby tests.
4. For a migration, the language being produced; treat the source language as context.
5. For generated code, the maintained source or generator language unless the user explicitly asks to edit generated output.
Ask one concise clarification only when those signals still do not identify the destination. Do not infer a language from personal preference or tool availability.
| Destination | Strong signals | Required skill |
|---|---|---|
| Bash or shell | `.sh`, a Bash shebang, shell CLI, automation, process wrapper, or Git/infra helper | `$shellscript-coder` |
| TypeScript or TSX | `.ts`, `.tsx`, `.mts`, `.cts`, `tsconfig.json`, a typed Node or React target | `$ts-coder` |
| Python | `.py`, `pyproject.toml`, Python service, package, script, or test target | `$python-coder` |
| Rust | `.rs`, `Cargo.toml`, Cargo workspace, crate, Rust CLI, service, library, or FFI target | `$rust-coder` |
JavaScript without a TypeScript target is not automatically TypeScript. An unsupported destination must be surfaced instead of silently routed to the nearest skill.
## Load the Canonical Skill
Resolve the user-level skill root as `${CODEX_HOME:-$HOME/.codex}/skills`. For every selected language:
1. Read the corresponding `SKILL.md` completely.
2. Read every reference that skill marks as required for the task.
3. Follow that skill as the execution contract, including its context gathering, language rules, direct implementation, verification, and correction loop.
The canonical entrypoints are:
- `${CODEX_HOME:-$HOME/.codex}/skills/shellscript-coder/SKILL.md`
- `${CODEX_HOME:-$HOME/.codex}/skills/ts-coder/SKILL.md`
- `${CODEX_HOME:-$HOME/.codex}/skills/python-coder/SKILL.md`
- `${CODEX_HOME:-$HOME/.codex}/skills/rust-coder/SKILL.md`
Do not substitute a generic coding workflow or launch a nested Codex process. The selected language skill executes directly in the current session.
After completing TypeScript or Python implementation, run `$code-simplifier`, when it is installed, on the changed production code before final verification.
## Mixed-Language Work
Use every language skill required by the requested output. Keep one shared task plan and one cross-language contract.
1. Identify the files and contract owned by each language.
2. Settle shared schemas, wire formats, command behavior, and error semantics before implementation.
3. Implement the contract owner first, then its consumers.
4. Apply each language skill only to its language's files.
5. Run each language's focused checks plus the smallest cross-language integration check.
Do not force a mixed task through one specialist and do not launch competing implementations of the same contract.
## Failure Boundary
The language skills are optional. If a selected language skill is not installed, follow the repository's own conventions and say which skill was missing; if an installed skill names a reference that is missing, search its installed roots, read it, and resume. Continue independent repository inspection meanwhile. Ask only for access or an artifact that investigation proves only the owner can supply; do not park the task or emulate unread instructions.
© sno-ai · Apache-2.0 · sno-ai/sno-station-skills
Similar skills
All skills for Agent setup: memory, context, orchestration →codex-coder by other authors comes first.