markmdev

markmdev/meridian

Plugin Claude Code

Agent enforcement framework — context injection, planning gates, session learning.

markmdev/meridian

Agent

Reviews architecture — either existing code or proposed plans. Use during planning to validate approach, or after changes to check structural health.

markmdev/meridian

Agent

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.

markmdev/meridian

Agent

Deep code review that finds real bugs — logic errors, data flow issues, pattern inconsistencies. Returns structured findings to the calling agent.

markmdev/meridian

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.

markmdev/meridian

Agent

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.

markmdev/meridian

Agent

Use when you have a detailed, unambiguous implementation spec (e.g., "add export for function X in file Y"). Executes the spec, runs typecheck/tests, reports results. Spawn multiple in parallel for independent tasks. Does NOT ask questions — reports ambiguity and stops.

markmdev/meridian

Agent

Documents planned work in Pebble before implementation. Creates appropriate structure (epic, task, or bug fix) based on scope.

markmdev/meridian

Agent

Validate a plan before implementation. Use before exiting Plan mode. Pass the plan file path and any additional context files. Returns JSON with findings and score (must reach 9+ to proceed).

markmdev/meridian

Command

Handle CodeRabbit AI review cycles after creating a PR.

markmdev/meridian

Command

Think through a problem on paper before acting.

markmdev/meridian

Command

Start a work-until loop that keeps you working on a task until completion.

markmdev/meridian

Hook

Runs when a session starts on startup, clear and compact, executing context-injector.py, session-cleanup.py and save-injected-files.py via python3 (3 commands). From markmdev/meridian.

markmdev/meridian

Hook

Runs when the agent finishes a response, executing work-until-stop.py and stop-checklist.py via python3 (2 commands). From markmdev/meridian.

markmdev/meridian

Hook

Runs after a tool call finishes for ExitPlanMode tool calls, executing action-counter.py and plan-approval-reminder.py via python3 (2 commands). From markmdev/meridian.

markmdev/meridian

Hook

Runs before the agent uses a tool for Task tool calls, executing reviewer-root-guard.py via python3. From markmdev/meridian.

markmdev/meridian

Hook

Runs when you submit a prompt, before the agent sees it, executing action-counter.py, plan-mode-tracker.py and instruction-reminder.py via python3 (3 commands). From markmdev/meridian.

markmdev/meridian

Hook

Runs before the context is compacted, executing session-transcript.py and session-learner.py via python3 (2 commands). From markmdev/meridian.

markmdev/meridian

Hook

Runs when a session ends, executing session-learner.py and session-transcript.py via python3 (2 commands). From markmdev/meridian.

markmdev/meridian

Skill Claude CodeCodex

Scan all .md files in the project and add or fix YAML frontmatter (summary + readwhen) so they can be discovered by context routers like Reflex.

markmdev/meridian

Skill Claude CodeCodex

Create or update .meridian/docs/ knowledge files for a module or directory. Produces reference docs with frontmatter for context routing.

markmdev/meridian

Skill Claude CodeCodex

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.

markmdev/meridian

Skill Claude CodeCodex

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.

markmdev/meridian

Skill Claude CodeCodex

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…