SebbaFlow

Browser automation via agent-browser. Use when the user wants to browse, interact with, or inspect web pages.

Review agent-facing knowledge (rules, AGENTS.md, CONVENTIONS.md, README.md, domain docs) for staleness and accuracy. Use when the user asks to audit, clean, or prune knowledge. Also use when they're confused by a rule/doc that seems wrong — treat that as the starting point for a broader audit.

Reflect on session, update rules, commit with jj.

Adversarial design interview.

Ingest sources into the wiki.

Wiki health checks.

Query the personal wiki.

Read-only code review of jj changes.

Interactive chunk-by-chunk code review using jj.

Persist observations to wiki inbox.

Plan and implement features with TDD.

Query code quality status from pitchfork background watchers (tests, lint, typecheck, format). Use when you want to check if tests pass, code is formatted, or lint is clean — without running checks manually.

Correct patterns for using jj (jujutsu) version control. Load this when you need to create revisions, move between changes, or perform any jj operation. Complements the commit skill (which handles commit-time concerns like message generation and rule reflection).

Manage development tools, tasks, and environment variables with mise (mise-en-place). Use when installing or switching tool versions, running project tasks, configuring per-project environments, or editing mise.toml files.

Control herdr from inside it. Manage workspaces and tabs, split panes, spawn agents, read output, and wait for state changes — all via CLI commands that talk to the running herdr instance over a local unix socket. Use when running inside herdr (HERDR_ENV=1).

Manage GNU Stow packages — install, uninstall, handle conflicts, add new stowable scripts, and resolve AGENTS.md symlink collisions. Use when installing/uninstalling stow packages, debugging symlink issues, or adding new tools to SebbaFlow.