Run any Skill in Manus with one click

codex-advise

Stars4

Forks0

UpdatedJuly 17, 2026 at 06:36

Cross-model second opinion from OpenAI Codex — `codex-run advise --context` reviews the current session, or pipe a brief. Triggers on "ask codex", "codex review", "second opinion", or the "Cross-model review" rules.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

motoki317

motoki317/dotfiles

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

name	codex-advise
description	Cross-model second opinion from OpenAI Codex — `codex-run advise --context` reviews the current session, or pipe a brief. Triggers on "ask codex", "codex review", "second opinion", or the "Cross-model review" rules.

Codex advisor

Cross-model outside view from OpenAI Codex. codex-run advise reads the prompt from stdin; codex-run --help lists the flags.

codex-run advise --context                                    # review the current session ("advise me", no brief)
codex-run advise --context < brief.md                         # session + a specific question
codex-run advise -C <repo> --log /tmp/codex.jsonl < brief.md  # cold review of a repo (no session)

--context sends the session to OpenAI. Codex sees your actions, not your thinking or injected context — put load-bearing reasoning in the brief and point Codex at the files.
A gate call (~/.claude/rules/process.md) runs foreground — wait for the verdict; background only a non-gating opinion.
Read-only by default; -s workspace-write lets Codex run tests — only when asked. stdout is the verdict.
A dropped call prints session: <id>; codex-run advise --resume <id> < followup.md continues that review — a network drop, or a follow-up on the same context — instead of a cold call. Resume only after the call exits.
Source: ~/.config/home-manager/scripts/{codex-run,session-transcript} (Go, built onto PATH by home-manager).

More from this repository

same repository

address

motoki317/dotfiles

Run a PR's full review-fix cycle — wait for review and CI, fix failures, evaluate and reply to comments, then commit and push. Use whenever a PR was just opened or updated — the post-Ship phase of the Orchestrator loop.

2026-07-184

motoki317/dotfiles

Push the current branch and create a pull request with a title and description derived from the commit history. Use when the user asks to open a PR — the Ship step of the Orchestrator loop, always user-triggered.

2026-07-184

codex-work

motoki317/dotfiles

Delegate a task's implementation wholesale to OpenAI Codex (`codex-run work`) — the whole requirements document in one long autonomous run — keeping policy, orchestration, and acceptance in the main loop. Use at the Implement step of the Orchestrator loop, for any multi-part build.

2026-07-174

define

motoki317/dotfiles

Define requirements before implementation — clarify constraints and design policy, then write a requirements spec and task breakdown for the Implementer to a gitignored plan file. Use at the Plan step of the Orchestrator loop, or whenever a request's scope needs pinning down before building. Never implements; the plan file is its only write.

2026-07-174

investigate

motoki317/dotfiles

Root-cause investigation — enumerate competing hypotheses, verify each with evidence, suggest a fix but never apply it. Use when an error, failing test, or anomaly needs diagnosing before any fix is written; implementation hands off to the Implementer.

2026-07-174

skill-creator

motoki317/dotfiles

Create, improve, and evaluate skills. Use when the user wants to create a skill from scratch, edit or optimize an existing one, run evals or benchmarks on it, or optimize its description for better triggering accuracy.

2026-07-174

name	codex-advise
description	Cross-model second opinion from OpenAI Codex — `codex-run advise --context` reviews the current session, or pipe a brief. Triggers on "ask codex", "codex review", "second opinion", or the "Cross-model review" rules.

Codex advisor

Cross-model outside view from OpenAI Codex. codex-run advise reads the prompt from stdin; codex-run --help lists the flags.

codex-run advise --context                                    # review the current session ("advise me", no brief)
codex-run advise --context < brief.md                         # session + a specific question
codex-run advise -C <repo> --log /tmp/codex.jsonl < brief.md  # cold review of a repo (no session)

--context sends the session to OpenAI. Codex sees your actions, not your thinking or injected context — put load-bearing reasoning in the brief and point Codex at the files.
A gate call (~/.claude/rules/process.md) runs foreground — wait for the verdict; background only a non-gating opinion.
Read-only by default; -s workspace-write lets Codex run tests — only when asked. stdout is the verdict.
A dropped call prints session: <id>; codex-run advise --resume <id> < followup.md continues that review — a network drop, or a follow-up on the same context — instead of a cold call. Resume only after the call exits.
Source: ~/.config/home-manager/scripts/{codex-run,session-transcript} (Go, built onto PATH by home-manager).