claude

os

Working-protocol plugin: foreman orchestration, contrarian review, session-end, delivery-lifecycle, ADHD-shaped reporting, frontend design judgment, the three foreman agents, and two context-discipline hooks.

0 on GitHubby arivodeauxv5.3.1MITupdated 1 month agoworkflow
/

Plugin os from marketplace arivodeaux-startup in arivodeaux/startup. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (6)

  • contrarian-review

    Fires before anything is presented to the user as done or reaches a user-facing surface, and on request for adversarial QA. Implements Guardrail 5, the Contrarian Gate. Runs an independent fresh-context os:foreman-verifier that publishes a verifiable contract before building starts, then re-verifies

  • delivery-lifecycle

    Fires when starting work inside a delivery project, or when a project's STATE.md says UNINITIALIZED. Session mechanics for bounded delivery projects (first-run init with the UNINITIALIZED sentinel, tasks/init.md and the 8-field Brief; session-start routine over STATE.md, lessons, blockers, Next line

  • foreman

    Fires for multi-file or multi-stage tasks, or on: orchestrate, delegate, foreman mode, save tokens, multi-agent, farm this out, big task on a budget. Orchestration protocol: delegation tickets, status vocabulary, escalation ladder, verification discipline, and the run ledger.

  • frontend-design

    Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

  • report-style-adhd

    Fires on every response for the rest of the session, injected at session start by a SessionStart hook. Shapes output for a reader with ADHD - lead with the outcome, number multi-step content, restate state each turn, one concrete next action, no preamble or recap.

  • session-end

    Fires at the end of any real work session, when the user says wrap up, close out, or session end, and before a long pause. Distills the session into dated, verdict-tagged lessons, updates STATE.md or the machine-mode running log, promotes repeat lessons toward rules, and summarizes what was built pl

Subagents (3)

  • foreman-scout

    FAST reconnaissance agent. Read-only codebase or filesystem scanning, locating relevant files and symbols, extracting facts. Dispatched by the orchestrator for recon tickets; not for judgment or modification.

  • foreman-verifier

    Fresh-context verifier. Receives the original task verbatim, the diff or changed paths, the acceptance criteria, and pointers to surrounding code, but never the worker's reasoning or self-report. Assumes the work is broken until it personally reproduces evidence otherwise. Read-only against source;

  • foreman-worker

    WORKHORSE implementation agent. Executes exactly one delegation ticket end-to-end (code, scripts, refactors, tests, docs) and reports back in the four-status contract. Dispatched by the orchestrator, optionally with a per-invocation model override (opus for heavy reasoning).

Hooks (2)

  • SessionStart

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/inject-report-style.py"

  • PreToolUse

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/guard-large-read.py"

View source on GitHub

More from arivodeaux/startup

All 3 plugins →

Project lifecycle skills: retire-project, next-free-port, deploy-cloudflare (Tier-3 gated).

3 skills

0

Browse the hub's live catalogs (frontend, backend, component libraries, free APIs, open-source and government repos).

2 skills

0

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

9 skills · 1 command · 8 agents

wshobson/agents 42,461

beads

claudecodex

AI-supervised issue tracker for coding workflows

1 skill · 1 agent · hooks

gastownhall/beads 28,698

MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows

18 skills

MiniMax-AI/skills 13,828

worktrunk

claudecodex

Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.

2 skills · hooks

max-sixty/worktrunk 12,481

gsd-core

claude

GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.

72 skills · 72 commands · 64 agents · hooks

open-gsd/gsd-core 11,494

Maintain os?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins3 plugins