Dev & Engineering multi-backendcodeagent-wrappercodexgeminiopencodeparallel-executiongit-worktreeagent-presets

Codeagent Multi-Backend Orchestration Skill

Run AI code tasks across Codex, Claude, Gemini, and OpenCode backends through one codeagent-wrapper command, with parallel multi-agent orchestration built in.

FollowSkills review · FSRS-2.0
Use with care
51/ 100 5-point scale 2.6 / 5
1 2 3 4 5 6
1Trust12 / 25 · 2.4/5

Data flow is transparent; worktree isolation, read-only agent presets, and explicit allowed/disallowed tool enumeration help safety. Major deductions: --skip-permissions exists and CODEAGENT_SKIP_PERMISSIONS defaults to true, CODEX_BYPASS_SANDBOX defaults to true — dangerous defaults that bypass user confirmation and sandboxing; no rollback guidance. Mid-range score.

2Reliability10 / 20 · 2.5/5

Internally consistent docs with exit-code table, progress-frame handling, failure output format, topological dependency sorting with cycle detection; CI runs Go tests for codeagent-wrapper. Capped at 10 per static rules: tests cover the wrapper, not this skill's key paths, and failure feedback is unverified by execution.

3Adaptability9 / 15 · 3.0/5

Scenarios, boundaries (read-only vs develop agents), input/output formats and triggers are well described. Deducted for full dependence on four overseas CLIs (Codex/Claude/Gemini/OpenCode) with poor mainland-China reachability and no Chinese-language support.

4Convention9 / 15 · 3.0/5

Clear layered structure, AGPL-3.0 license, version 6.7.0 in package.. Deducted: no skill-level changelog, no version mapping, no known-limitations section, unverified publisher, maintenance responsibility only implicit.

5Effectiveness6 / 15 · 2.0/5

Multi-backend orchestration, parallel tasks, session resume and structured JSON output are fully described and plausible. Deducted: static review cannot confirm outputs are directly usable, no representative-output evidence, and users must pre-install four external CLIs, raising cost.

6Verifiability5 / 10 · 2.5/5

Real CI (three-OS matrix) plus a committed Go test suite covering the skill's core dependency codeagent-wrapper provide partial corroboration. Capped at 5 per static rules; no independent reproduction of the skill path itself.

Evidence confidence:Low Reviewed Sep 09, 2026 Reviewed revision f2e75c1263a2
Before you use it
  • CODEAGENT_SKIP_PERMISSIONS and CODEX_BYPASS_SANDBOX default to true: deployment silently bypasses permission prompts and sandboxing. Explicitly set them to false and audit any --skip-permissions usage.
  • Core function depends on four overseas CLIs (Codex/Claude/Gemini/OpenCode); effectively unusable from mainland-China networks without a proxy or substitute backends.
  • Static review only — no code was executed: orchestration effectiveness, failure feedback and output quality are unverified; pilot in an isolated repository before sensitive or production use.
  • develop-type agents directly modify code and run tests; always pair with --worktree so changes are recoverable.
Review evidence [1][2][3][4][5][6][7][8]
See the full review method →

What does this skill do, and when should you use it?

The codeagent skill teaches Claude Code how to invoke the codeagent-wrapper CLI to dispatch coding tasks to four pluggable backends: Codex, Claude, Gemini, and OpenCode. It bundles agent presets (code-explorer, code-architect, code-reviewer, develop), auto-injects language best-practice skills based on project files, supports git worktree isolation, and runs parallel tasks with dependency-based topological sorting. Execution defaults to background, producing structured JSON reports and resumable session IDs. It ships inside the stellarlinkco/myclaude repository under the AGPL-3.0 license as one of eleven bundled skills.

Reads marker files in the working directory (go.mod, package., etc.) to auto-select skills for prompt injection; builds and executes codeagent-wrapper commands specifying backend, model, reasoning effort, and agent preset; reads task configs from stdin in --parallel mode, sorts them with Kahn's algorithm, and runs independent tasks concurrently; executes write tasks inside isolated git worktrees (branch do/{task_id}); produces per-task pass/fail reports with log paths and structured JSON output, returning a SESSION_ID for follow-up runs.

  1. Developers who want to mix backends in one project: hand algorithm-heavy work to Codex, docs and prompt engineering to Claude, UI prototyping to Gemini.
  2. Engineers leading large refactors: run read-only code-explorer and code-architect passes first, then apply changes via develop in an isolated worktree.
  3. Team leads running multi-phase pipelines (explore → design → implement → review) in parallel, with dependencies scheduling task order automatically.
  4. Maintainers of polyglot monorepos who rely on auto-detection to inject Go/Rust/Python/frontend best practices per project.
  5. Automation pipelines needing auditability, using --output to emit structured JSON results plus per-task logs.

What are this skill's strengths and limitations?

Pros
  • One entry point unifies four backends, letting you match model to task type.
  • Built-in read-only/writable agent presets and auto skill injection cut down on hand-written prompts.
  • Parallel execution includes dependency topological sorting and circular-dependency detection.
  • Worktree isolation and structured JSON output make it easy to wire into existing automation.
  • Session resume support and per-task logs simplify debugging failed runs.
Limitations
  • Requires the external codeagent-wrapper binary plus at least one backend CLI, raising setup cost.
  • The repo ships no test suite or standalone evidence for this skill; the README mostly describes the whole module collection.
  • AGPL-3.0 is viral for closed-source commercial integration; commercial use requires a separate license.
  • Some behavior assumes Claude Code workflow conventions (background execution, Bash tool parameters) and needs adjustment in other clients.
  • The source provides no version number, stability guarantees, or cost comparison across backends.

How do you install this skill?

Run the interactive installer: npx github:stellarlinkco/myclaude (use --list to see installable items, --install-dir for a custom directory, --force to overwrite). After install, codeagent-wrapper lives at ~/.claude/bin/ and this skill at ~/.claude/skills/codeagent/. The source does not document a supported way to install this single skill in isolation from the collection.

How do you use this skill?

Single task: codeagent-wrapper --agent develop --skills golang-base-practices - . <<'EOF' …task… EOF (run via the Bash tool in the background). Parallel: codeagent-wrapper --parallel <<'EOF', defining tasks with ---TASK---/---CONTENT--- blocks containing id, agent, dependencies, etc. Long tasks emit [codeagent-progress] frames — do not kill them; resume with resume <session_id>. Configure via ~/.codeagent/config.(yaml||toml) or CODEAGENT_-prefixed environment variables.

More skills from this repository

All from stellarlinkco/myclaude

Dev & Engineering

Dev End-to-End Development Workflow

An extreme-lightweight end-to-end dev workflow: clarifies requirements, orchestrates multi-backend parallel execution, and enforces 90% test coverage.

Dev & Engineering

do — Feature Development Orchestrator

Turns feature work into a five-phase workflow where parallel sub-agents handle code understanding, design, implementation and review — the orchestrator never writes code itself.

Dev & Engineering

OmO Multi-Agent Orchestrator

Trigger with /omo and dispatch code analysis, bug investigation, and fixes to the minimal right mix of agents — no fixed pipeline.

Dev & Engineering

Harness Long-Running Agent Framework

Keeps agent tasks running across sessions: automatic progress checkpointing, interruption recovery, failure rollback, and dependency-ordered task scheduling.

Design & Frontend

Prototype Prompt Generator

Turns vague UI requirements into structured, production-ready prototype prompts with complete design specs, ready to hand to any AI tool or developer.

Productivity & Collaboration

Product Requirements (Interactive PRD Skill)

Turns vague feature ideas into a professional PRD through interactive dialogue and a 100-point quality score, only generating at 90+.

Dev & Engineering

SPARV Five-Phase Workflow

A Specify→Plan→Act→Review→Vault workflow with external memory files that pushes vague requirements through to verifiable delivery in one pass, instead of coding on assumptions.

Dev & Engineering

Test Cases Generator

Turns PRDs or user requirements into structured test cases covering functional, edge, error and state transition scenarios.

Automation & Ops

Browser Automation Skill

Drive Chrome directly over the Chrome DevTools Protocol — navigate, run JS, screenshot, and pick DOM elements — with no MCP server required.

Dev & Engineering

Skill Install — Secure Skill Installer

Installs Claude skills from any GitHub repository with automated pre-install security scanning that blocks malicious code and backdoors.

Related skills