--- title: "portable-agent-skills" description: "Agent workflow skills that behave the same in Claude Code and Codex CLI, with a portability contract enforced in CI." canonical: https://agentpluginsdirectory.com/plugins/portable-agent-skills last-updated: 2026-10-11 --- # portable-agent-skills Agent workflow skills that behave the same in Claude Code and Codex CLI, with a portability contract enforced in CI. - Slug: portable-agent-skills - Publisher: rosslevinsky - Repository: https://github.com/rosslevinsky/portable-agent-skills - Manifest: plugin.json - Version: 2026.10.2 - License: Apache-2.0 - Category (editorial): agent-tooling - Skills: 19 (clarify, commit, cyw, demo-video, diff-review, extract-hooks, handoff, plan-duel, plan-init-v1, plan-init, plan-phase-v1, plan-phase, plan-run-v1, plan-run, review-panel, security-review-codebase, tdd, web-verify, xc) - MCP servers: 0 - Stars: 6 - Repository created: 2026-04-16 - Repository last pushed: 2026-10-07 - Publisher type: User - Listing: https://agentpluginsdirectory.com/plugins/portable-agent-skills - Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json ## What portable-agent-skills does, in the publisher's words A collection of portable, cross-runtime agent skills for Claude Code and Codex CLI. Each skill is a standalone workflow document (SKILL.md) that both runtimes can execute with equivalent outcomes. AI coding agents benefit from reusable, well-shaped workflows, "write a failing test first, then implement," "audit this codebase for security issues," "break a large task into committable phases." This repository packages those workflows as plain-markdown SKILL.md files that both Claude Code (Anthropic) and Codex CLI (OpenAI) can invoke, with equivalent behaviour enforced by an automated portability contract. One install command drops 16 skills into the right places for both runtimes. CI enforces a contract that forbids runtime-specific tool names, requires a fallback wherever a skill leans on a companion skill, and flags private paths before they ship. Installs are copies, never links: so an edit an agent makes to its own instructions gets read here before it ships back out. From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/rosslevinsky/portable-agent-skills/HEAD/README.md ## Skills - clarify: Explains the thing the user is asking about in plain, jargon-free English, straight from its source, this conversation, pasted text, a document, code, a term, or a link. No repository required. With no argument, explains the last response. Use when the user invokes /clarify, or says "I don't under… - commit: Stage the paths a change touched, named, never a `git add -A` sweep of the tree, then write a descriptive commit message based on a diff review and commit. Pushes only when the request asked to publish: "commit and push" or "push my changes" push; "stage and commit" or a bare /commit stop at the… - cyw: Multi-pass review of recent work to catch errors, gaps, and improvements. Use when the user invokes /cyw, or asks to 'check your work', 'review what you just did', 'is this correct/complete?', 'what's missing?', 'what needs fixing?'. Runs a structured 3-phase loop: critical review, fix, verify. Rep… - demo-video: On-demand guided-tour walkthrough video of a built feature, the last skill in the v2 workflow. Drives an existing Playwright / frontend setup through the primary flow slowly with pauses, records video, and derives timed subtitles from as-built.md and test-step timing; optional background music. Ne… - diff-review: Independent, diff-first code review of a change set. A dedicated reviewer reads the diff first with fresh context, no reliance on the implementation rationale, and reports correctness findings without editing the tree. Distinct from author self-review: it is the second, adversarial pair of eyes a… - extract-hooks: Audit TSX files, identify non-UI logic, and extract it into custom hooks. Use when the user invokes /extract-hooks, or says "extract hooks", "move logic out of components", or "separate logic from layout". - handoff - plan-duel: Iterative plan refinement between Claude and Codex. Each agent writes an initial plan using a condensed v2 plan methodology embedded in the skill (mirroring plan-init's content model), then they alternately critique and incorporate the other's best ideas, with a judge checking for convergence after… - plan-init-v1: Create a plan document using the superseded v1 workflow, it writes no `Format: v2` marker and no execution.md tracker. Use when the user invokes /plan-init-v1, or is continuing an existing v1 plan; new work belongs to /plan-init. Interviews the user to fill gaps, explores the codebase for context,… - plan-init: Create a structured project plan document for a task, the current planning suite. Interviews the user to fill gaps, explores the codebase, then produces a master plan.md stamped with the `Format: v2` marker and a `Suite` row, and, when the plan lives under plans/, registers it in the plans/READM… - plan-phase-v1: Work breakdown for a superseded v1 plan, it writes phases.md, not execution.md. Use when the user invokes /plan-phase-v1, or is continuing an existing v1 plan produced by /plan-init-v1; a plan carrying the `Format: v2` marker belongs to /plan-phase. Reads the plan document and breaks it into order… - plan-phase: Work breakdown for a plan: the current planning suite. Reads a `Format: v2` plan.md, proposes an ordered phase list (noting in prose which phases are independent and which reconciles them), then writes one phase document per phase plus the checkbox execution.md tracker (never phases.md). UI phases… - plan-run-v1: Execute a superseded v1 plan: one driven by phases.md rather than execution.md. Use when the user invokes /plan-run-v1, or is continuing an existing v1 plan produced by /plan-init-v1 + /plan-phase-v1; a plan carrying the `Format: v2` marker belongs to /plan-run. Reads the master plan and phases.md… - plan-run - review-panel - security-review-codebase - tdd - web-verify - xc Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.