Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

codex

Étoiles5

Forks0

Mis à jour5 février 2026 à 21:22

This skill should be used when the user asks to "use Codex CLI", "codex exec", "get a Codex second opinion", or "run a Codex review" as a separate agent.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

treygoff24

treygoff24/autonomous-dev-kit

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

SKILL.md

readonly

name	codex
description	This skill should be used when the user asks to "use Codex CLI", "codex exec", "get a Codex second opinion", or "run a Codex review" as a separate agent.

Codex CLI Delegation

Use Codex CLI as a parallel agent with its own context window. Prefer codex exec for headless runs and codex for the TUI.

When to Use

Code review or spec/plan review
Debugging second opinion
Parallel implementation in an isolated worktree

Quickstart

codex exec --sandbox read-only "Review src/auth against SPEC.md. Focus on security and tests."
codex exec --full-auto --cd ../worktrees/task-3 "Implement Task 3 from IMPLEMENTATION_PLAN.md."

Exec Inputs

PROMPT string, or - to read stdin.
--image, -i attaches one or more images to the first message.

Config and Model Overrides

--model, -m overrides the configured model (e.g., gpt-5-codex).
--profile, -p selects a profile from ~/.codex/config.toml.
--config, -c key=value overrides config values (repeatable).
--oss uses the local open source provider (requires Ollama).
--cd, -C sets the working directory before execution.
--skip-git-repo-check allows running outside a Git repo.

Safety Controls

--sandbox, -s: read-only | workspace-write | danger-full-access.
--ask-for-approval, -a: untrusted | on-failure | on-request | never.
--full-auto: sets --ask-for-approval on-request and --sandbox workspace-write.
--dangerously-bypass-approvals-and-sandbox, --yolo: no approvals or sandbox.
--add-dir: grant extra write roots.
--search: enable web search tool usage.

Output and Scripting

--json / --experimental-json: newline-delimited JSON events.
--output-last-message, -o <path>: write final assistant message to a file.
--output-schema <path>: validate the final response against a JSON Schema.
--color <always|never|auto>: control ANSI output.

Session Control

codex resume [SESSION_ID] or codex resume --last [--all].
codex exec resume [SESSION_ID] to continue non-interactive runs.
codex fork [SESSION_ID] to branch a prior interactive session.

Notes

Global flags apply to subcommands; place them after the subcommand (e.g., codex exec --oss ...).
Codex runs with its own context window; include all necessary context in the prompt.

Plus depuis ce dépôt

même dépôt

requesting-code-review

treygoff24/autonomous-dev-kit

Use when completing tasks, implementing major features, or before merging to verify work meets requirements - runs review in a forked code-reviewer agent

2026-03-015

autonomous-loop

treygoff24/autonomous-dev-kit

Activate autonomous loop mode for persistent development sessions. **CRITICAL:** Always activate this AFTER completing spec and implementation plan, BEFORE beginning implementation. This is what makes autonomous builds actually autonomous—the Stop hook enforces completion criteria.

2026-03-015

brainstorming

treygoff24/autonomous-dev-kit

Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes

2026-03-015

debugging-systematic

treygoff24/autonomous-dev-kit

Apply systematic root cause analysis and debugging methodologies to diagnose and fix bugs, test failures, and unexpected behavior. Use when encountering production issues, investigating test failures, diagnosing performance problems, tracing error sources through call stacks, analyzing logs and stack traces, reproducing inconsistent bugs, debugging race conditions, investigating memory leaks, or applying scientific method to problem-solving before proposing fixes.

2026-03-015

orchestrator

treygoff24/autonomous-dev-kit

Activate orchestrator mode. You coordinate specialists, you don't implement. MAXIMIZE parallelism with task-builder. MAXIMIZE quality with code-reviewer, codex, gemini. Speed + Quality through delegation, not through doing work yourself.

2026-03-015

task-builder

treygoff24/autonomous-dev-kit

Execute ONE task in parallel with other task-builders. ALWAYS SPAWN MULTIPLE for independent tasks. ORCHESTRATOR: You coordinate, you don't implement. Spawn N task-builders for N unblocked tasks. Maximum parallelism = maximum speed = maximum quality (each task gets focused attention).

2026-03-015

Codex CLI Delegation

Use Codex CLI as a parallel agent with its own context window. Prefer codex exec for headless runs and codex for the TUI.

When to Use

Code review or spec/plan review

Debugging second opinion

Parallel implementation in an isolated worktree

Quickstart

codex exec --sandbox read-only "Review src/auth against SPEC.md. Focus on security and tests." codex exec --full-auto --cd ../worktrees/task-3 "Implement Task 3 from IMPLEMENTATION_PLAN.md."

Exec Inputs

PROMPT string, or - to read stdin.

--image, -i attaches one or more images to the first message.

Config and Model Overrides

--model, -m overrides the configured model (e.g., gpt-5-codex).

--profile, -p selects a profile from ~/.codex/config.toml.

--config, -c key=value overrides config values (repeatable).

--oss uses the local open source provider (requires Ollama).

--cd, -C sets the working directory before execution.

--skip-git-repo-check allows running outside a Git repo.

Safety Controls

--sandbox, -s: read-only | workspace-write | danger-full-access.

--ask-for-approval, -a: untrusted | on-failure | on-request | never.

--full-auto: sets --ask-for-approval on-request and --sandbox workspace-write.

--dangerously-bypass-approvals-and-sandbox, --yolo: no approvals or sandbox.

--add-dir: grant extra write roots.

--search: enable web search tool usage.

Output and Scripting

--json / --experimental-json: newline-delimited JSON events.

--output-last-message, -o <path>: write final assistant message to a file.

--output-schema <path>: validate the final response against a JSON Schema.

--color <always|never|auto>: control ANSI output.

Session Control

codex resume [SESSION_ID] or codex resume --last [--all].

codex exec resume [SESSION_ID] to continue non-interactive runs.

codex fork [SESSION_ID] to branch a prior interactive session.

Notes

Global flags apply to subcommands; place them after the subcommand (e.g., codex exec --oss ...).

Codex runs with its own context window; include all necessary context in the prompt.