Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By markmdev
Orchestrate agent-enforced dev sessions with context injection, planning validation gates, and session learning to audit code quality, observability gaps, UI states, generate knowledge docs, plan features via interviews, and automate iterative fixes through git/PR loops until completion.
npx claudepluginhub markmdev/meridianReviews architecture — either existing code or proposed plans. Use during planning to validate approach, or after changes to check structural health.
Finds dead code, pattern drift, over-engineering, and refactoring opportunities. Use after completing large tasks, at the end of feature work, or when code has gone through many iterations.
Deep code review that finds real bugs — logic errors, data flow issues, pattern inconsistencies. Returns structured findings to the calling agent.
Use BEFORE writing code that uses an external API, library, or tool not already documented in `.meridian/api-docs/`. Researches via web scraping and builds comprehensive knowledge docs with current versions, API operations, limits, and gotchas.
Use for broad codebase research when you don't know where to look, need to understand "how does X work?", or want comprehensive findings across many files. Returns file paths, line numbers, code snippets, and negative results. Read-only — cannot modify files.
Scan all .md files in the project and add or fix YAML frontmatter (summary + read_when) so they can be discovered by context routers like Reflex.
Create or update .meridian/docs/ knowledge files for a module or directory. Produces reference docs with frontmatter for context routing.
Audit code for silent error swallowing, fallbacks to degraded alternatives, backwards compatibility shims, and UI that fails to show errors to the user. Finds and fixes all occurrences in the specified scope.
Audit code for observability gaps — debug logs left in, errors caught without being logged, missing context on log entries, untracked slow operations. Uses the app's existing observability tooling exclusively.
Interview-driven planning methodology that produces implementation-ready plans. Always use this skill INSTEAD of EnterPlanMode — it provides structured interviewing (20-40 clarifying questions), exhaustive parallel codebase exploration (5-15 Explore agents), verbatim requirements capture, and automated plan validation via plan-reviewer (must score 9+). Use for new features, refactoring, architecture changes, migrations, or any non-trivial implementation work.
Matches all tools
Hooks run on every tool call, not just specific ones
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Opinionated workflow guides and best practices - the preacher's proven patterns for Claude Code projects
Harness for Claude Code — skills, /harness:* slash commands, persona subagents, lifecycle hooks, and MCP tools without per-repo `harness setup`. Sibling plugins exist for Cursor, Gemini CLI, and Codex.
Complete project development toolkit: 23 agents, 23 slash commands, 29 lifecycle hooks, and 69 reusable skills for Claude Code workflows
Claude Copilot — a framework of specialized agents, skills, commands, and hooks that give Claude persistent memory, expert methodology, and task tracking. Agents cover architecture (ta), engineering (me), QA (qa), design (sd/design), DevOps (do), documentation (doc), and knowledge onboarding (kc).
Autonomous session orchestrator for Claude Code - manages multi-phase development workflows
Session-level orchestration — wave planning, VCS integration, quality gates, persistence, and safety checks
Runs pre-commands
Contains inline bash commands via ! syntax
Runs pre-commands
Contains inline bash commands via ! syntax
Share bugs, ideas, or general feedback.
Meridian makes Claude Code more reliable on real projects.
It adds persistent project context, smarter session handoff, and lightweight workflow enforcement so Claude is less likely to lose the plot halfway through a long task.
Claude Code is great at short bursts. It gets shakier when work stretches across a big repo, multiple sessions, or a lot of moving pieces.
Common failure modes:
CLAUDE.md drift out of focus during long runsMeridian closes those gaps without asking you to completely change how you work.
WORKSPACE.md, project docs, and supporting prompts stay available across sessions.meridian/docs/ can advertise when they should be readMeridian is intentionally opinionated, but it stays behind the scenes. You still talk to Claude normally.
Meridian is most useful if you use Claude Code for:
If you mostly use Claude Code for tiny one-off edits, Meridian is probably overkill.
/plugin marketplace add markmdev/claude-plugins
/plugin install meridian@markmdev
Inside the repo you want to use with Meridian:
curl -fsSL https://raw.githubusercontent.com/markmdev/meridian/main/install.sh | bash
That creates a .meridian/ folder with the project-side files Meridian uses.
Meridian hooks are provided by the plugin. The scaffolded .meridian/ directory gives the plugin project-specific files to read from.
Update the project scaffolding:
meridian-update
Or:
curl -fsSL https://raw.githubusercontent.com/markmdev/meridian/main/install.sh | bash
Update the plugin itself:
/plugin update meridian@markmdev
Check the installed project version:
cat .meridian/.version
Meridian has two halves:
Installed through Claude Code's plugin system:
These live with the plugin and are updated with /plugin update.
Installed into your repo by install.sh:
.meridian/
├── SOUL.md
├── WORKSPACE.md
├── config.yaml
├── docs/
├── prompts/
├── scripts/
└── lib/
The installer preserves project state on update, including:
WORKSPACE.md.meridian/workspace/.meridian/plans/.meridian/config.yamlMeridian hooks into Claude Code lifecycle events and adds a little structure at the moments where Claude usually drifts.
Current behavior includes:
The goal is not to micromanage Claude. The goal is to keep it oriented.
.meridian/WORKSPACE.mdThe running handoff for the project. Keep it current, short, and operational.
.meridian/docs/Put durable project docs here. Meridian scans these docs and can steer Claude toward the right one when a task matches its frontmatter hints.
Minimal frontmatter:
---
summary: What this doc covers
read_when:
- keyword or situation
- another keyword
---
.meridian/config.yamlProject-level behavior toggles.
Current built-in options include:
pebble_enabled: false
stop_hook_min_actions: 15
session_learner_mode: project
Recent versions also support extra stop-checklist items and custom instruction reminders.