Personal collection of Claude Code plugins, published as a marketplace.
tc: input.json to output.json, diffed against expected.json.tk, a git-backed issue tracker for AI agents.~/.claude/.notes/, structured decision log, and timestamped journal entries.Three plugins work together to manage project knowledge:
| Store | Plugin | Contract | Purpose |
|---|---|---|---|
specs/ | spec-driven-dev | Strongest | Behavioral truth — Gherkin scenarios, verified before shipping |
docs/ | (none needed) | Strong | Durable reference — maintained, authoritative |
notes/DECISIONS.md | project-notes | Medium | What was decided — concise dcn-xxxx entries |
notes/ | project-notes | Weak | Working knowledge — may go stale |
notes/journal/ | project-notes | Weakest | Timestamped snapshots — decay over time |
project-knowledge provides routing rules for deciding where information should live and where to look for it.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub a3lem/my-claude-plugins --plugin python-rulesMinimal file-based ticket system with dependency tracking for humans and AI agents
Skills for using shablon, a CLI that renders Jinja2 templates from a .shablon/ directory into a project tree.
File-based inter-agent messaging for parallel Claude Code sessions
Spec-driven development system with structured directories for requirements, design, tasks, and notes
Automatically prompt execution of Session Setup steps from CLAUDE.md on session start
Hybrid RAG rule retrieval + session-aware workflow enforcement. Injects relevant coding rules via a 5-stage pipeline (BM25 + vector + graph traversal + RRF ranking) and enforces mode-based workflow gates (plan -> tests -> implementation).
Automatic context engineering — observes your coding sessions and generates rules, suggestions, skills, and hooks so Claude gets smarter on your codebase over time
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Continuous self-referential AI loops for interactive iterative development, implementing the Ralph Wiggum technique. Run Claude in a while-true loop with the same prompt until task completion.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.