dotfiles

Best practices for working with Go codebases. Use when writing, debugging, or exploring Go code, including reading dependency sources and documentation.

Autonomous orchestration loop for hive hc tasks. The high-capability manager model reads pending tasks, delegates implementation to cheaper worker sub-agents, critically reviews their output, and commits only code that passes quality checks. Runs to completion without stopping to ask questions.

Post-implementation design re-evaluation. After a feature reaches a working state through iteration, step back and re-examine what actually got built: are the data structures and algorithms the right fit for the access patterns that emerged, can code paths that grew through iteration be consolidated, and what iteration residue (tests for abandoned designs, dead flags/scaffolding, debug logging) should be deleted. Produces a tiered proposal report and applies only approved changes. Use when the user says "rethink this", "step back and re-evaluate", "is this the right design/data structure", "apply CS fundamentals", or wants a design pass on a working feature branch before PR. Not for bug-hunting (/review) or expression-level polish (/simplify) — this questions the design those skills preserve.

Orchestrate parallel claude and codex CLI agents through tmux to deliver a feature end-to-end. The orchestrator delegates planning, work, and review to spawned agents in tmux windows; it does NOT write or edit code itself. User-invoked only.

Open the current branch's diff (or a specific PR) in Plannotator's browser-based code review UI and act on the returned feedback. Use when the user says "review my changes in plannotator", "open the diff for review", "review this PR in plannotator", "let me annotate the diff", or returns to a session to gate code the agent produced.

Single-pass code review of the current branch (or a diff) that routes the changes to relevant concerns, dispatches fresh-context reviewer sub-agents, verifies findings to strip false positives, and reports a ranked, evidence-backed review. Use when the user asks to review local changes, a branch, or a PR before it goes to humans.

Spawn codex as an independent external reviewer in a new tmux window. Codex performs a general PR review and publishes findings back via hive messaging. Use standalone for an external second opinion, or alongside /review to run both concurrently.

Deep-dive spec interviewer. Reads a file or requirement, analyzes it against the codebase, then conducts a rigorous 1-on-1 interview using AskUserQuestion to produce a comprehensive, opinionated specification document. Acts as a collaborative architect with active pushback.

Show changes compared to base branch (defaults to main). Use when the user asks what changed, wants a summary of branch differences, or says "catch me up".

Open a plan, research, or design doc in Plannotator's browser UI for human review and act on the returned annotations. Use when the user says "review the plan", "open the doc in plannotator", "let me annotate the research", "review the latest doc", or returns to a session to gate work the agent produced.

Write and analyze Go benchmarks using modern patterns and tools

Mini research → plan for small, self-contained changes. Use for well-scoped tasks like bug fixes, adding a single field, or small feature additions where the overall system impact is limited. Faster than /research + /plan-write — single sub-agent per step, no user interview, lighter output.

Create detailed implementation plans through interactive research and iteration. Use when the user wants to plan a feature, task, or ticket before implementing. Expects a research document as input. Interviews the user, then uses sub-agents to draft and review the plan before writing a structured plan to .hive/plans/.

Monitor CI and review comments for the current branch's PR. Use with /loop to automatically fix failing CI checks or address PR review comments at a set interval. Trigger when the user says "watch CI", "monitor my PR", "fix CI in a loop", "babysit my PR", "keep an eye on CI", or similar phrases. Exits cleanly when CI passes and no unresolved comments remain.

Generate a design doc from template and save to .hive/design-docs/. Use when the user asks to create, draft, or write a design doc, design proposal, or technical proposal.

Create a PR from current branch changes. Use when the user asks to open a PR, create a pull request, or says "pr this up".

Research codebase comprehensively using parallel sub-agents. Use when the user asks for deep research, wants to understand how a feature works, or needs thorough analysis of patterns and architecture across the codebase.

Wrap up a work session - organize commits, push branch to remote, update task state

Start the next hive hc task, prioritizing work related to current branch

Save documents to the .hive/ context directory (symlinked into Obsidian). Use when the user asks to save, write, or put a document into their notebook.

Create a hive hc epic from the current plan file, inserting the ENTIRE PLAN TEXT into the epic and creating subtasks to track all work items.

Gitea/Forgejo CLI and API usage. Use when working with tea CLI commands or making direct API calls to Gitea/Forgejo instances.

Use the scooter CLI for find and replace operations across codebases. Use when the user asks for bulk find-and-replace, renaming symbols across files, codebase-wide text substitution, or when sed/awk would be too fragile for multi-file replacements.

Expert guidance for building TUI applications with the Charm Bracelet ecosystem (Bubbletea, Lipgloss, Bubbles). Use when implementing components, styling, or working with MVU architecture.

Specialized guidance for testing TUI applications with Bubbletea, including golden file testing, component testing, and integration testing with teatest.