Wraps OpenAI Codex CLI to run independent code reviews, adversarial challenges, and consult sessions.
npx skills add https://github.com/raghavbadhwar/rstack --skill codex-raghavbadhwar
Please help me install this Agent Skill. Skill: codex Source: https://github.com/raghavbadhwar/rstack/tree/main/codex Command: npx skills add https://github.com/raghavbadhwar/rstack --skill codex-raghavbadhwar
codex review as a pass/fail gate on your changes, catching issues the authoring model may have missed. - Adversarial challenge mode: Actively tries to break your code and assumptions, stress-testing logic before release. - Consult with session continuity: Ask Codex anything and keep follow-up context across questions, useful for architecture debates and debugging. - Use Case: Before merging a feature branch, invoke the review mode to get a pass/fail verdict from Codex, then use challenge mode on any risky logic it flags, and finally consult on how to fix the findings. ## Quick Start Ask the agent to run a codex review of the current branch diff and report whether it passes or fails.High-intent search queries and answers about installing and using this skill.
Invoke the codex review mode, which runs the Codex CLI against your current diff and returns a pass/fail verdict. It acts as an independent reviewer separate from the model that wrote the code.
Review mode performs a pass/fail diff review, challenge mode adversarially tries to break your code, and consult mode answers open questions with session continuity for follow-ups. Each mode wraps a different Codex CLI invocation.
Yes, the preamble detects headless, spawned, and interactive session kinds. In headless runs it blocks instead of prompting, and in spawned sessions it auto-chooses recommended options without interactive questions.
The gstack preamble runs one-time onboarding prompts for telemetry, proactive suggestions, and routing rules. Each prompt writes a marker file so it only appears once per machine or project.
Yes, consult mode maintains session continuity so follow-up questions retain prior context. This makes it suitable for multi-turn architecture discussions or iterative debugging.
darkmatterReview code diffs and implementation plans for correctness and regressions.
shftwstMerges gate-cleared pull requests through the faff merge-gate interlock and emits a delivery-outcome contract block.
jkhowlandRun OpenAI Codex CLI against the current diff to review code changes.
adamtpangAutomates the release workflow of testing, reviewing, versioning, and creating pull requests for git branches.