Agent Plugins Marketplace
← All plugins

catalyst-ops

v0.4.1

How Catalyst Shift operates (HOW_WE_BUILD v2). Three skills: next (the pickup loop — top Linear card → build → in-session adversarial pass → /ship with auto-merge on → next card, 650k context budget, handoff for a fresh session), ways-of-working (three homes + the build method: /next, adversarial review as a required check, auto-merge on everything, recommend-ask-proceed with hard stops), and decision-governance (proposed-vs-decided labelling, ratification rules). The verify skill and verify-gate hook are retired (the CI adversarial review replaces them). Behavior only; canon content stays in the strategy doc and docs/HOW_WE_BUILD.md.

Claude Code3 Skills

By Catalyst Shift0 GitHub starsUpdated 1 hour ago

Directory evidence

Runtimes
Claude Code
Parsed components
3 skill or MCP entries
Source updated
Sep 29, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install catalyst-ops for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install catalyst-ops@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/Catalyst-Shift/catalyst-shift-plugins

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is catalyst-ops/.

Plugin files

catalyst-ops/
├── .claude-plugin/plugin.json
├── skills/decision-governance/SKILL.md
├── skills/next/SKILL.md
└── skills/ways-of-working/SKILL.md

Included Skills3

decision-governanceskills/decision-governance/SKILL.md

Guard how decisions get recorded for Catalyst Shift — in Linear issues, in HQ documents, and against canon. Use whenever you are about to file, retitle, or update an issue that asserts a decision; whenever you generate a document that cites one; and whenever your output would change strategy, pricing, ICP, positioning, what we sell, or commit us to an external partner. Also use when Kevin, Lucas, or Keith says "we decided", "we're going with", "this supersedes", or asks you to amend canon.

nextskills/next/SKILL.md

Pick up and finish the next Linear card for this repo, end to end — build, attack, ship with auto-merge on, then take the next card. Use when Kevin types /next (optionally with a card ID like CAT-123 or a repo/project hint like "lbl"), or says "grab the next thing", "keep going", "pick up work" in a code repo. Code repos only — never for strategy, documents or Cowork work. HOW_WE_BUILD v2 §2–§5.

ways-of-workingskills/ways-of-working/SKILL.md

Catalyst Shift's operating canon — the three homes (repos = built, Linear = happening, SharePoint = decided/produced) and the build method (issue-as-spec, kanban, concept vs harden PRs, /next pickup, adversarial review as a required check, auto-merge on everything, recommend-ask-proceed with hard stops). Use at the START of any session that will file work, merge code, write copy about the product, save a deliverable, or start an agent task — and whenever deciding where something goes or whether a claim is backed.

Plugin manifests1

catalyst-ops/.claude-plugin/plugin.json
{
  "name": "catalyst-ops",
  "version": "0.4.1",
  "description": "How Catalyst Shift operates (HOW_WE_BUILD v2). Three skills: next (the pickup loop — top Linear card → build → in-session adversarial pass → /ship with auto-merge on → next card, 650k context budget, handoff for a fresh session), ways-of-working (three homes + the build method: /next, adversarial review as a required check, auto-merge on everything, recommend-ask-proceed with hard stops), and decision-governance (proposed-vs-decided labelling, ratification rules). The verify skill and verify-gate hook are retired (the CI adversarial review replaces them). Behavior only; canon content stays in the strategy doc and docs/HOW_WE_BUILD.md.",
  "author": {
    "name": "Catalyst Shift",
    "email": "[email protected]"
  },
  "homepage": "https://github.com/Catalyst-Shift/catalyst-shift-plugins",
  "repository": "https://github.com/Catalyst-Shift/catalyst-shift-plugins"
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[catalyst-ops on Agent Plugins Marketplace](https://pluginsmp.com/plugins/catalyst-ops)