Claude-Mods: Project Plan & Roadmap

Goal: A centralized repository of custom Claude Code commands, agents, and skills that enhance Claude Code's native capabilities with persistent session state, specialized expert agents, and streamlined workflows.

Created: 2025-11-27 Last Updated: 2026-03-09 Status: Active Development

Current Inventory

Component	Count	Notes
Agents	23	Domain experts + git-agent background worker
Skills	64	Operational skills, CLI tools, workflows, dev tasks
Commands	3	Session management (sync, save) + experimental (canvas)
Rules	5	CLI tools, thinking, commit style, naming, skill-agent-updates
Output Styles	4	Vesper, Spartan, Mentor, Executive
Hooks	3	pre-commit-lint, post-edit-format, dangerous-cmd-warn

Completed Milestones

Core Infrastructure

Session continuity (/save, /sync)
Plan persistence to docs/PLAN.md
Agent genesis system (/spawn)
Installation scripts (Unix + Windows)

Expert Agents (22)

Languages: Python, TypeScript, JavaScript, Go, Rust, SQL, Bash
Frontend: React, Vue, Astro
Backend: Laravel, PayloadCMS, CraftCMS
Infrastructure: AWS Fargate, Cloudflare, Wrangler
Testing: Cypress
Databases: PostgreSQL, SQL patterns
Specialized: Claude-architect, Project-organizer

Skills (38)

Python patterns (8): async, cli, database, env, fastapi, observability, pytest, typing
Claude Code internals: debug, headless, hooks, templates
Workflows: git, data-processing, structural-search, task-runner
Patterns: REST, SQL, security, testing, tailwind
Development: explain, spawn, atomise, setperms, introspect, review, testgen

Commands (3)

Session: /save, /sync
Experimental: /canvas

Documentation

ARCHITECTURE.md - Extension system guide with authority levels
README.md - Project overview and usage
AGENTS.md - Quick reference

Enhancement Roadmap

Tier 1: High Impact, Low Effort

Output Style Variations

Style	Personality	Best For
Vesper	Sophisticated British wit	General work (exists)
Spartan	Minimal, bullet-points only	Quick tasks
Mentor	Patient, educational	Learning, onboarding
Executive	High-level summaries	Non-technical stakeholders

Rules Expansion

Rule	Purpose	Status
`cli-tools.md`	Modern CLI preferences	Done
`thinking.md`	Extended thinking triggers	Done
`commit-style.md`	Conventional commits format	Done
`naming-conventions.md`	Component naming patterns	Done
`code-review.md`	Review checklist	Future
`testing-philosophy.md`	Coverage expectations	Future

Hook Implementations

Hook	Purpose
`pre-commit-lint.sh`	Run linter before committing
`post-edit-format.sh`	Auto-format after edits
`dangerous-cmd-warn.sh`	Confirm destructive commands

Tier 2: High Impact, Medium Effort

Agent Gaps

Agent	Why It Matters
`docker-expert`	Containerisation is ubiquitous
`github-actions-expert`	CI/CD complexity
`nextjs-expert`	App Router specifics
`testing-architect`	Strategy decisions
`api-design-expert`	OpenAPI, versioning

Skill Gaps

Skill	Purpose
`debug`	Systematic debugging workflow
`migrate`	Framework/version upgrades
`refactor`	Safe refactoring
`secure`	Security audit checklist

Skill Parity

Languages needing Python-level depth:

typescript-patterns/
go-patterns/
rust-patterns/

Tier 3: Strategic Expansions

Template System: Project scaffolding via /scaffold
MCP Server Catalog: Curated high-value servers
Feedback System: Track tool effectiveness

Priority Matrix

                    IMPACT
                    High         Low
            +-----------+-----------+
       Low  | Output    | Templates |
            | Styles    |           |
    EFFORT  | Rules     | MCP       |
            | Hooks     | Catalog   |
            +-----------+-----------+
       High | Agent     | Analytics |
            | Gaps      |           |
            | Skills    | Lang      |
            |           | Parity    |
            +-----------+-----------+

Immediate Next Steps

Command-to-Skill Consolidation (Complete)

Most commands have been converted to skills for better discovery and on-demand loading. See docs/COMMAND-SKILL-PATTERN.md.

Completed conversions:

/testgen → skills/testgen/
/review → skills/review/
/explain → skills/explain/
/spawn → skills/spawn/
/atomise → skills/atomise/
/setperms → skills/setperms/
/introspect → skills/introspect/

Remaining as commands:

/sync - Session bootstrap (paired with /save)
/save - Session persistence (paired with /sync)
/canvas - Experimental (Warp-specific)

Planned Work

Create rules/commit-style.md
Create rules/naming-conventions.md
Create Spartan output style
Create Mentor output style
Create Executive output style
Add debug-ops skill (systematic debugging workflow)
Add 3 hook implementations (lint, format, safety)
Add migrate-ops skill (framework/language upgrades)
Add refactor-ops skill (safe refactoring patterns)
Add scaffold skill (project scaffolding)
Add perf-ops skill (performance profiling)
Add log-ops skill (JSONL/log analysis)
Add docker-expert agent
Install lnav on Windows for log analysis

Open Questions

Should agents auto-update from a central registry?
How to handle agent versioning?
Should there be a "recommended agents" list per project type?

Guiding Principle

The best enhancements solve problems you've already felt. Follow the pain.

Plan managed by /save command. Last updated: 2026-03-09

PLAN.md 6.1 KB History Raw