By alleneubank
Reusable planning, handoff, verification, and workflow skills for agents.
Use when starting dev servers, watchers, tilt, or any process expected to outlive the conversation. Provides zmx session management patterns for long-lived processes.
Use when the user says they are stepping away and the agent should continue without interactive approvals
Use when running e2e tests, debugging test failures, or fixing flaky tests. Covers failure taxonomy, fix rules, and workflow. Never changes source code logic or API without spec backing.
Use when auditing how well the shared agent instructions (AGENTS.md, skills) hold up in real sessions — sampling transcripts via recall, scoring them against the gap rubric, and turning findings into ratified amendments
Use when preparing clean, logical git commits from an existing working tree
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 agent-workflowsCodex-powered code review gate. Creates a review checkpoint that triggers Codex CLI review when Claude exits.
Iterative Ralph loops with Codex CLI review gates at completion. Claude works until done, then Codex reviews before allowing exit.
Linear CLI integration for Claude Code - manage issues, teams, and projects
Linear CLI integration for Claude Code - manage issues, teams, and projects
Hook-backed activity tracking for the agent-statusline renderer across Claude Code and Codex CLI.
Harness-native ECC operator layer - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.