Command Claude Code
A command for adding structured logs, measurements, and request traces to a software module. These records help show what an application is doing and how it performs.
Command Claude Code
Manages multiple named execution pipelines in one project and selects one per run or per code-agent host. Use when several agents (Claude Code, pi, opencode) need different model routing.
Command Claude Code
A command for creating a detailed work plan for a feature, bug fix, refactor, or experiment. It saves the plan in a memory bank, a project folder used to keep planning information.
Command Claude Code
A command for opening a GitHub pull request from the current branch. A pull request is a proposed code change that others can review before it is merged.
Command Claude Code
Manages rule profiles and stack presets — personalizes the configurable rules layer without weakening the immutable safety baseline. Use when tuning rules to a role, stack or architecture.
Command Claude Code
A guided code-refactoring command that changes a chosen module, file, or subsystem while aiming to keep its behavior unchanged.
Command Claude Code
A code-review command that examines uncommitted changes against the project's plans, architecture, coding principles, tests, and security needs.
Command Claude Code
A command that rebuilds the automatic sections of `roadmap.md` from plan files and their front matter, which is metadata at the top of a Markdown file.
Command Claude Code
A command that creates three connected planning files for a software feature: requirements, design, and tasks.
Command Claude Code
A code security review command that checks for common vulnerabilities, exposed secrets, and unsafe dependencies across several programming languages.
Command Claude Code
A session-start command that loads the project's Memory Bank, a set of files containing saved project context and status.
Command Claude Code
A command that runs the project's tests, summarizes failures, and suggests fixes. Tests are automated checks that compare the software's behavior with expected results.
Command Claude Code
A command that rebuilds a Markdown table linking requirements to project plans and tests. It reads requirement files, plan files, and test markers, then records what is planned or covered.
Command Claude Code
A command that runs an existing Memory Bank workflow for planning, implementing, checking, reviewing, and completing development work. The workflow can use project plans or specification tasks.
Agent Claude Code
Systematic-debugging specialist for memory-bank. Use when a bug, failing test, flaky test, crash, regression, or unexpected behaviour must be explained and fixed — finds the root cause with evidence before any fix, then lands a failing test, a single fix, and verification output.
Agent Claude Code
This is a partial, not an agent. /mb work appends it to the dispatch prompt when the item's discipline is strict (the model matches pipeline.yaml: discipline.strictmodels). It restates the engineering core as hard rules. Where it is stricter than the core, it wins.
Command Claude Code
A command for managing coding rules stored in CLAUDE.md, AGENTS.md, and optional project RULES.md files. It can select built-in rules, add personal rules, change settings such as architecture or coverage, and control whether test-driven development (TDD) is required.
Skill Claude CodeCodex
A writing guide for producing clear, concise prose in English or Russian.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: