By alleneubank
Language, tooling, and delivery-practice skills for agentic coding.
Use when automating iOS Simulator interactions, capturing screenshots/video, or inspecting accessibility via AXe CLI.
Use when working with atlas.hcl, Atlas CLI commands, schema HCL/SQL files, or migration planning and reviews, including Atlas v1.1 security, data, and exporter capabilities.
Use when creating, reviewing, or updating a BRIEF.md (the quality law for a surface), defining what "good"/shippable means, or setting up a verified autonomous loop.
Use when working with Canton Network participants, DAML smart contracts, Splice applications, or debugging LF version and package ID issues.
Use when building or maintaining Electrobun desktop apps in TypeScript, including electrobun.config.ts, electrobun/bun or electrobun/view imports, BrowserWindow/BrowserView usage, updater flows, and distribution artifacts.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Portable agent runtime profile for Codex CLI and Claude Code.
This repo owns one public, shareable instruction file and a small marketplace of installable plugins. It replaces ad hoc dotfile sync for agent instructions and skills without taking ownership of private local overrides.
AGENTS.md is the canonical shared user-level instruction file.~/.codex/AGENTS.md should be a symlink to AGENTS.md.~/.claude/CLAUDE.md should be a symlink to AGENTS.md.plugins/engineering-practices contains language, tooling, and quality skills.plugins/agent-workflows contains reusable workflow skills.Private notes do not belong in this repo. Use ~/.codex/AGENTS.override.md,
~/.claude/CLAUDE.local.md, or another local-only file outside this repository.
Clone the profile repo from GitHub:
git clone https://github.com/alleneubank/agent-profile.git ~/.agent-profile
cd ~/.agent-profile
Check current runtime state:
./install.sh --check
Apply safe fixes:
./install.sh --fix
If an instruction target is a real file instead of a symlink, the installer refuses to replace it. To back it up and replace it with the repo symlink:
./install.sh --fix --replace-existing
The installer registers local marketplaces during --fix only when doing so will
not mutate a config file owned by another git worktree. Manual marketplace
commands are useful when installing directly from GitHub or when you want plugin
installation separate from instruction-file setup.
Install plugins from GitHub:
codex plugin marketplace add alleneubank/agent-profile
codex plugin add engineering-practices@agent-profile
codex plugin add agent-workflows@agent-profile
claude plugin marketplace add alleneubank/agent-profile
claude plugin install engineering-practices@agent-profile
claude plugin install agent-workflows@agent-profile
./scripts/validate.sh
The old codex-reviewer and ralph-reviewed Claude hook plugins are retired.
Use modern rl skills and commands for review gates and autonomous loops.
Each plugin is versioned independently; the version field in its manifest is the
single source of truth. scripts/validate.sh enforces 3-way parity across
plugins/<name>/.claude-plugin/plugin.json, plugins/<name>/.codex-plugin/plugin.json,
and the plugin's entry in .claude-plugin/marketplace.json — name/version/description
must match. The root marketplace.json (Codex-style) carries no versions.
Semver, per plugin:
MAJOR — breaking change to a skill's contract (a skill removed/renamed, or its
invocation/behavior changed in a way callers depend on).MINOR — a new skill, or a new backward-compatible capability/section.PATCH — clarifications, fixes, or wording changes to existing guidance.Release steps:
version in all three manifests for the plugin (keep them identical).chore(release): <plugin> vX.Y.Z.git tag -a <plugin>-vX.Y.Z -m "<plugin> vX.Y.Z — <summary>".Tags mirror the manifest version and are human-facing markers only — plugins install by
name from the marketplace (claude plugin install <plugin>@agent-profile), which reads the
manifest, not git tags. The legacy unscoped v1.1.0 tag predates this scheme.
npx claudepluginhub alleneubank/agent-profile --plugin engineering-practicesIterative Ralph loops with Codex CLI review gates at completion. Claude works until done, then Codex reviews before allowing exit.
Codex-powered code review gate. Creates a review checkpoint that triggers Codex CLI review when Claude exits.
Linear CLI integration for Claude Code - manage issues, teams, and projects
Linear CLI integration for Claude Code - manage issues, teams, and projects
Reusable planning, handoff, verification, and workflow skills for agents.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Matt Pocock's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Design fluency for frontend development. 1 skill with 23 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls