claudecodex

software-engineering-team

Name: software-engineering-team
Author: Agentrof

Software Engineering Team for approved analysis, solution and experience design, and a delivery-ready backlog.

1 on GitHubby Agentrofv2026.11.2Apache-2.0updated 2 days agoEngineering

Plugin software-engineering-team from marketplace agent-marketplace in agentrof/agent-marketplace. Commands read from the repo's manifest — 2 days 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 (13)

analyze
Defines testable outcomes, business rules and task boundaries when a request contains uncertainty or changes product behavior.
autopilot
Run authorized parallel delivery and bounded detection, resolution and retrospective loops under an explicit expiring grant.
companions-uninstall
Remove explicitly selected supported companions from the chosen hosts and verify their removal.
configure
Change explicit project settings, execution profiles or proof commands through their owning writer.
data-design
Designs and checks persistent data, relationships, ownership, isolation and migration behavior whenever a task changes stored state.
deliver
Delivers a requested change or task batch through focused analysis, implementation, proportionate verification and review to the authorized merge outcome.
experience-design
Designs and checks user-facing content, interaction and visual states for UI bugfixes, screens, journeys, navigation and workflows.
issue-report
Diagnose and locally verify a plugin repair, then prepare an anonymous linked upstream issue and pull request.
retrospective
Measure completed work and recurring failures, identify causal bottlenecks, and propose verified improvements without blocking delivery.
review
Independently checks a candidate against its outcome, contracts and risks, producing evidence-backed findings within a bounded correction loop.
setup
Bootstrap or migrate project-owned integration when required inputs are missing or incompatible.
solution-design
Chooses component boundaries, interfaces and implementation approach when a task changes architecture, technology or cross-component behavior.
verify
Selects and executes proportionate evidence for acceptance criteria, regressions and live behavior, including shared validation of compatible tasks.

Subagents (5)

critical-reviewer
Independent review of high-consequence invariants and evidence.
critical-worker
High-consequence design or implementation in an assigned workspace.
light-worker
Bounded mechanical work in an assigned workspace.
reviewer
Independent review of an immutable candidate using supplied evidence.
worker
Implementation or investigation in an assigned workspace.

Hooks (19)

SessionStart
python3 "${CLAUDE_PLUGIN_ROOT}"/scripts/hook_launcher.py scripts/team_guard.py register
SessionStart
python3 "${CLAUDE_PLUGIN_ROOT}"/scripts/hook_launcher.py scripts/retrospective_hook.py --host claude
UserPromptExpansion
python3 "${CLAUDE_PLUGIN_ROOT}"/scripts/hook_launcher.py skill-content/autopilot/scripts/autopilot.py hook user-prompt --host claude --entry software-engineering-team:autopilot --session-env CLAUDE_CO
UserPromptExpansion
python3 "${CLAUDE_PLUGIN_ROOT}"/scripts/hook_launcher.py skill-content/autopilot/scripts/autopilot.py hook native-watch --host claude
PreToolUse
python3 "${CLAUDE_PLUGIN_ROOT}"/scripts/hook_launcher.py scripts/worker_context.py claude
PreToolUse
python3 "${CLAUDE_PLUGIN_ROOT}"/scripts/hook_launcher.py skill-content/autopilot/scripts/autopilot.py hook native-dispatch --host claude
PreToolUse
python3 "${CLAUDE_PLUGIN_ROOT}"/scripts/hook_launcher.py scripts/autopilot_guard.py pre
PreToolUse
python3 "${CLAUDE_PLUGIN_ROOT}"/scripts/hook_launcher.py scripts/workspace_guard.py
PreToolUse
python3 "${CLAUDE_PLUGIN_ROOT}"/scripts/hook_launcher.py skill-content/autopilot/scripts/autopilot.py hook pre-question --host claude
PostToolUse
python3 "${CLAUDE_PLUGIN_ROOT}"/scripts/hook_launcher.py scripts/autopilot_guard.py post
PostToolUseFailure
python3 "${CLAUDE_PLUGIN_ROOT}"/scripts/hook_launcher.py scripts/autopilot_guard.py post
PostToolUseFailure
python3 "${CLAUDE_PLUGIN_ROOT}"/scripts/hook_launcher.py scripts/retrospective_hook.py --host claude
SubagentStart
python3 "${CLAUDE_PLUGIN_ROOT}"/scripts/hook_launcher.py skill-content/autopilot/scripts/autopilot.py hook native-register --host claude
SubagentStart
python3 "${CLAUDE_PLUGIN_ROOT}"/scripts/hook_launcher.py skill-content/autopilot/scripts/autopilot.py hook native-watch --host claude
UserPromptSubmit
python3 "${CLAUDE_PLUGIN_ROOT}"/scripts/hook_launcher.py skill-content/autopilot/scripts/autopilot.py hook native-watch --host claude
Stop
python3 "${CLAUDE_PLUGIN_ROOT}"/scripts/hook_launcher.py scripts/retrospective_hook.py --host claude
SessionEnd
python3 "${CLAUDE_PLUGIN_ROOT}"/scripts/hook_launcher.py scripts/retrospective_hook.py --host claude
SubagentStop
python3 "${CLAUDE_PLUGIN_ROOT}"/scripts/hook_launcher.py scripts/retrospective_hook.py --host claude
StopFailure
python3 "${CLAUDE_PLUGIN_ROOT}"/scripts/hook_launcher.py scripts/retrospective_hook.py --host claude

View source on GitHub

Similar plugins

mattpocock-skills

claude

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and withholds from agents exactly as it does CLAUDE.md, skipping any file the engine already loaded by import or link; a tool.call hook on Read attaches the ones under the project root as the engine attaches a nested CLAUDE.md. Under claude-md-and-agents-md every AGENTS.md is loaded beside CLAUDE.md. Under managed-only the project's and the person's instruction files are dropped and the organization's managed ones kept. Under claude-md the engine's walk stands alone. claude-md-or-agents-md is the default.

anthropics/claude-code 155,476

agent-skills

claudecodex

Production-grade engineering skills covering every phase of software development: spec, plan, build, verify, review, and ship.

25 skills · 4 agents

addyosmani/agent-skills 116,782

agentic-qe-fleet

claude

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

ruvnet/ruflo 81,589

AAS Security Engineer

codex

Install the "AAS Security Engineer" workflow plugin from Agentic Awesome Skills.

12 skills

sickn33/agentic-awesome-skills 49,620

reverse-engineering

claudecodex

Binary reverse engineering, malware analysis, firmware security, and software protection research for authorized security research, CTF competitions, and defensive security

4 skills · 3 agents

wshobson/agents 42,461

Maintain software-engineering-team?

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 pluginslisted