Skip to content
weside.aiweside docs

The `we` plugin

The we plugin is the tooling layer of Agentic Product Ownership. It adds a family of /we:* skills to Claude Code that cover the full chain — the four altitudes, the build pipeline, and the quality gates around them. One install, in your own repo, currently at version 6.8.0.

What it is

Section titled “What it is”

27 /we:* entries in total — 23 skills plus 4 commands — plus 13 supporting agents the plugin dispatches on its own (a Council’s role-lenses, the AC reviewer, the doc architect, the PR creator, and the static/test runners) that you never invoke directly.

Why it matters to you

Section titled “Why it matters to you”

The plugin never hardcodes one ticketing tool. Skills speak in generic actions — “create ticket”, “move to In Review” — and map them to whatever you have: Jira (via MCP), GitHub Issues (via the gh CLI), or plan-only mode when there is no tracker at all. PRs go through GitHub; the CI-review step pulls findings from CI and Claude review.

How you use it

Section titled “How you use it”
Terminal window
/we:setup    # detect stack + ticketing tool, set up project vision and the crew

/we:setup runs once per project. It asks six skippable questions — your stack, your ticketing tool, test discipline, whether to set up a vision doc and DoR/DoD, the .weside/ config, and the repo crew — and you can skip any of them. After that you are working.

The full catalogue:

Terminal window
# Plan altitudes (Solo) + Council
/we:vision /we:saga /we:epic /we:story /we:refine   # formulate one artifact per altitude
/we:council /we:meet                                 # multi-lens deliberation + decomposition


# Build
/we:orchestrate   # the Lead: dispatches workers, integrates, one PR, one CI pass
/we:develop        # the worker: builds one chunk, local gates, commit, push, stop
/we:ci-review      # collect CI + review findings, fix, push once


# Quality gates (standalone)
/we:ac-review /we:static /we:test /we:pr


# Status, handoff, close-out
/we:standup   # where this branch stands — ticket, PR, CI, your one next move
/we:map       # a read-only status tree across every plan
/we:merged    # close out after a human merge
/we:retro /we:handoff


# Project and companion
/we:onboarding /we:sideload /we:materialize   # crew setup, cross-repo context, load your companion


# Other
/we:find-dead-code /we:prototype /we:grill /we:codex-task

Limits & edge cases

Section titled “Limits & edge cases”
  • No account, no nagging. The plugin works fully on its own; a weside account is an upgrade, not a gate. With one, a backing MCP server connects your Companion — persistent project memory across sessions, vision held as Companion goals, context that survives a /clear. /we:materialize is what loads that identity into a session.
  • Version drift is possible. This page describes 6.8.0 (we/.claude-plugin/plugin.json); a skill’s exact behavior can move between releases.
  • Delivery stays human. /we:orchestrate never merges or closes a ticket; /we:merged runs only after you’ve done both.

Where next

Section titled “Where next”