bendrucker

Hand the current conversation off to a fresh background agent that picks up the work immediately, so you can step away and track it independently. Use when the user wants to background the current work, keep going without them, continue in a separate session,…

Get a cross-model second opinion on a code change from GPT via the Copilot CLI, then triage what it finds. Use when the ask names GPT, Copilot, a second model, or a cross-model check, and as the cross-model pass on a change that clears the review gate.

Query Claude Code session history via a DuckDB index over `~/.claude/projects/`. Use when asked about Claude Code activity ("how many tokens today?", "what did I work on this week?", "which sessions discussed X?") or instead of reading, grepping, or jq-ing…

Request Ben's own review of the working diff or a document before it leaves the machine, for architecture and slop rather than bugs. Runs after the mechanical passes (code-review or simplify, comments:audit). Use for "get my review", "let me look at this…

Review a pull request when requested by a peer. Use when reviewing PRs, providing code review feedback, or analyzing proposed changes. Supports GitHub and GitLab. Pass --triage to summarize a PR and estimate its review effort without reviewing it.

Triage and batch-implement Claude-tagged Things todos as PRs for the claude config repo, discover improvement candidates from session history, or watch open PRs to implement review feedback and close shipped todos. Use when the user wants to work on their…

Finish a branch: infer which review passes the change warrants, run them, open the PR, babysit CI to green, triage bot comments, and refresh the body from a clean context.

Test-driven development. Use when building a feature or fixing a bug test-first, when the user asks for red-green-refactor, or when a change needs its tests written before its implementation.

Add a new cobra subcommand to the CLI

QA the honeycomb CLI against a live account to find bugs and feature gaps. Target one command or resource family for manual testing, or sweep everything before a release. Use when dogfooding the CLI, reproducing a bug, or producing a findings report mapped to…

Working with Honeycomb SLOs, burn alerts, and SLO history

Manage Honeycomb boards: create, update panels, configure visualizations, and review in Chrome. Activated by explicit mention of Honeycomb boards or /board invocation.

Design and build Honeycomb queries: calculations, filters, breakdowns, visualization selection, granularity tuning, and anti-patterns. Activated by explicit mention of Honeycomb queries or /query invocation.

Honeycomb CLI and MCP server usage — auth, queries, datasets, SLOs, boards, triggers, markers, columns, and raw API requests for observability workflows

Capture screenshots of the user's herdr/terminal setup so the model can see what it actually looks like. Use when the user asks for a visual review of their terminal, herdr sidebar, prompt, fonts, or pane chrome, or any case where text introspection (pane…

Add interactive prompts, spinners, styled logging, and pickers to shell scripts using gum. Use when editing a shell script and adding a prompt, asking for confirmation, wrapping a long-running command in a spinner, picking from a list, logging styled status…

DuckDB data layer over shell command history (atuin) for usage analysis. Use when analyzing how commands are actually used — frequency, alias/function candidates, argument patterns, sequences. Not for editing config, querying Claude Code sessions, or…

Analyze shell history and installed tools to suggest dotfiles improvements. Use when looking for missing aliases, functions, completions, or topics based on actual usage patterns. Trigger on "what aliases should I add", "what's missing from my dotfiles",…

ZSH completion system patterns and conventions. Use when implementing custom completion handling, writing completion files, or working with zsh autocomplete. Do not use when installing packages from homebrew, since that typically installs completions…

Work through UI comments left with the Agentation toolbar in the browser, hands-free, until the user stops. Use when asked to watch for feedback, take UI comments, or start a feedback loop.

Render a change to this site locally and look at it. Covers seeding a local D1 and R2, the URLs worth requesting, and screenshotting both themes at phone and desktop widths. Use when a change touches the cycling or code activity pages, route maps, photos, or…

Write and review Histoire component stories in this repo. Covers layout widths that survive a phone, initState and Hst* controls, logEvent, docs blocks, and the silent failures that produce no error. Use when creating or editing any *.story.vue file.

Manage route-agent project: check status, find next tasks, spawn parallel work. Use when starting work, checking progress, or asking "what's next?"

Promptfoo evaluation framework for testing and comparing LLM outputs. Use when writing eval configs, creating test cases, debugging eval runs, or working with assertions.

Start this app's dev server, drive it in a real browser, and run the repo's verification commands. Use when running, screenshotting, or QAing the app, confirming a change works in the running UI, driving a live API run, or measuring rendered styles such as…