Skill Claude CodeCodex
Diagnose and fix Catalyst setup issues. Validates tools, database, config, OTel, direnv, the Catalyst Cloud replica mirror, and thoughts. Automatically fixes what it can — creates directories, initializes the database, sets WAL mode, runs migrations. Use for new installs, upgrades, or when something isn't working.
Skill Claude CodeCodex
Validates YAML frontmatter on plugins//skills//SKILL.md and plugins//agents/.md against docs/frontmatter-standard.md and .claude/rules/plugin-editing.md: required fields, the disable-model-invocation/user-invocable polarity, allowed-tools vs tools, and skill-only fields that must not leak (model, category). Use when…
Plugin Claude Code
Research-driven development workflow with Linear integration, PM tools, and infrastructure research agents.
Instructions file CodexOpenCode
AGENTS.md instructions for coalesce-labs/catalyst, covering agents.md, what this repository is, agent philosophy, build & test and key principles.
Instructions file
Claude Code instructions for coalesce-labs/catalyst, covering claude code, loading & invocation, orchestration runtime, pull request review (codex) and code understanding (serena mcp).
Agent
You are a Catalyst Pattern Agent running in a Claude Managed Agents (CMA) cloud session. You operate on whichever target repo is bound at session creation, plus the coalesce-labs/thoughts knowledge repository, integrated with Linear and GitHub via MCP. You implement the Catalyst pattern — a set of conventions for how…
Plugin Claude Code
Complete development workflow: research → plan → implement → validate → ship. Includes research agents, planning tools, handoff system, Linear integration, and PM commands.
Agent
Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :).
Agent
Locates files, directories, and components relevant to a feature or task. Call codebase-locator with human language prompt describing what you're looking for. Basically a "Super Grep/Glob/LS tool" — Use it if you find yourself desiring to use one of these tools more than once.
Agent
You are a specialist at finding code patterns and examples in the codebase. Your job is to locate similar implementations that can serve as templates or inspiration for new work.
Agent
Research external resources including GitHub repositories, frameworks, libraries, and general web content. Uses Context7 for library docs, Exa for code search, and WebSearch/WebFetch for general web research.
Agent
Research GitHub PRs, issues, workflows, and repository structure using GitHub CLI (gh). Complements git operations with GitHub-specific metadata.
Agent
Research Linear tickets, cycles, projects, and milestones using Linearis CLI. Optimized for LLM consumption with minimal token usage (1k vs 13k for Linear MCP).
Agent
Research Sentry errors, releases, performance issues, and source maps using Sentry CLI and Sentry documentation. Combines CLI data with error pattern research.
Agent
The research equivalent of codebase-analyzer. Use this subagenttype when wanting to deep dive on a research topic. Not commonly needed otherwise.
Agent
Discovers relevant documents in thoughts/ directory (We use this for all sorts of metadata storage!). This is really only relevant/needed when you're in a reseaching mood and need to figure out if we have random thoughts written down that are relevant to your current research task. Based on the name, I imagine you can…
Skill Claude CodeCodex
Fast browser automation CLI for AI agents. ALWAYS use instead of Playwright MCP tools for web testing, screenshots, form filling, and UI verification. Use when user says "open in browser", "check the site", "take a screenshot", "fill the form", "test the UI", or any browser interaction. Also use as a fallback when a…
Skill Claude CodeCodex
Ask/decision tickets ("what needs me") — the Catalyst-wide SOP for raising a human decision as a Linear ticket, replying in-thread as the app actor, and closing it when the answer lands. Use whenever an agent needs a human to decide or click something, or for any ticket labelled catalyst-ask / ask/decision.
Skill Claude CodeCodex
Interactive walk-through of today's morning briefing. Loads the briefing markdown at thoughts/briefings/YYYY-MM-DD.md (built by morning-briefing), parses its decisions block, and walks the user through each open decision — approve / reject / defer, schedule a calendar entry, file a Linear ticket, launch a relay-ticket…
Skill Claude CodeCodex
Automatically analyzes code changes and creates git commits with conventional commit messages when the user indicates they want to save their work, commit changes, or says 'commit this', 'save my changes', 'let's commit'. Auto-detects commit type, scope, and ticket reference from branch name.
Skill Claude CodeCodex
Closing ritual for the AI-native estimation feedback loop. ALWAYS use when a ticket's PR has merged and merge-pr's post-merge deploy-verification (CTL-2232) has resolved a terminal sentinel for it — the relay-native trigger this skill now shares with ticket-retro and ticket-compound, see references/trigger.md…
Skill Claude CodeCodex
The ONE agent a human talks to. Use when a human comments on their Concierge — ticket, on the status board, or on any scope no steward owns; when a new project must be scaffolded from a request; or when an ask has gone unanswered. Owns the board, the ask inbox, and routing. Never commands a steward.
Skill Claude CodeCodex
Create handoff document for passing work to another session. ALWAYS use when the user says 'create a handoff', 'hand this off', 'save progress for later', 'I need to stop here', or when context usage is high (>60%) during implementation and work needs to continue in a fresh session.
Skill Claude CodeCodex
Create detailed implementation plans through an interactive process. ALWAYS use when the user says 'plan this', 'create a plan', 'let's plan the implementation', 'design the approach', or wants a structured TDD implementation plan before writing code. Works best after /research-codebase.